# vulnfix-ai

> vulnfix-ai: 69 Keryn rules for javascript, typescript, python (65 error, 4 warning).

Source: https://keryn.dev/rules/vulnfix-ai/

69 rules · Keryn Software Licence · rules 0.8.0 · [all packs](https://keryn.dev/rules/)

**How to read a rule**

- **Severity**: How bad the finding is if it is real: `error` fails a default gate, `warning` and `info` do not.

- **Confidence**: **P0** exploitable as written; **P1** dangerous in context; **P2** a heuristic or a posture check: confirm by reading the code.

- **False-positive risk**: **low**: an exact API or flag, so hits are almost always real; **medium**: the pattern is legitimate in many programs, so check each hit; **high**: it finds a lead to confirm, so expect benign hits.

- **Edge**: The relationship the finding sits on. **reaches**: content or traffic gets to a thing; **calls**: one thing invokes another; **reads**: one thing reads from another; **writes**: one thing writes to another; **sends**: data leaves for another party; **grants**: authority is given or left unchecked; **depends_on**: something relies on a component it does not verify; **trusts**: one party believes another without evidence. The boundary it crosses, when there is one: **user->prompt** (untrusted input reaching a prompt); **model->code** (model output reaching code, a shell, a query or a page); **secret->outside** (a secret leaving the trusted side); **supply-chain** (code, models or prompts pulled in from outside).

- **Taxonomy chips**: References for readers who work in OWASP LLM 2025, OWASP Agentic, CWE or NIST AI RMF. They say where a rule belongs, not that a framework is satisfied.

## vulnfix-ai-ai_js_openai_browser

`error` javascript, typescript openai

CWE-1295 (exposure): Runs the OpenAI/LLM client in the browser, exposing the API key.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-1295](https://keryn.dev/rules/?cwe=CWE-1295) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse)

Also reported under the older id `vulnfix-ai-ts_ai_openai_browser`.

**Try it: a snippet that triggers this rule**

Written for this page, not taken from any project. Save it as `web/src/ask.js` and scan it with `keryn scan web --verbose`; the finding below appears.

```js
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: window.localStorage.getItem("api_key"),
  dangerouslyAllowBrowser: true,
});

export async function ask(question) {
  const r = await client.chat.completions.create({
    model: "gpt-4o-mini",
    messages: [{ role: "user", content: question }],
  });
  return r.choices[0].message.content;
}
```

Checked with Keryn's browser engine when this page was built: it reports `vulnfix-ai-ai_js_openai_browser` at line 3 (error, proof 1). The rule's own logic is not published, so it cannot run in this tab; the pack list in the [playground](https://keryn.dev/playground/) shows what does.

## vulnfix-ai-ai_js_lc_allow_dangerous

`error` javascript, typescript vulnfix-ai

CWE-502 (unsafe-flag): Opts into unpickling/loading untrusted serialized data.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

Also reported under the older id `vulnfix-ai-ts_ai_lc_allow_dangerous`.

## vulnfix-ai-ai_js_dangerous_html

`error` javascript, typescript react

CWE-79 (insecure-output-handling): Renders raw HTML in React; if it carries LLM/markdown/user output, sanitize (DOMPurify).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-79](https://keryn.dev/taxonomies/cwe/#cwe-79-cross-site-scripting) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution)

Also reported under the older id `vulnfix-ai-ts_ai_dangerous_html`.

## vulnfix-ai-ai_hardcoded_provider_key

`error` javascript, python, typescript vulnfix-ai

CWE-798 (secret-exposure): a hardcoded AI provider API key. Move it to an environment variable / secret manager and rotate the exposed key.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-798](https://keryn.dev/taxonomies/cwe/#cwe-798-use-of-hard-coded-credentials) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse)

**Try it: a snippet that triggers this rule**

Written for this page, not taken from any project. Save it as `src/llm.py` and scan it with `keryn scan src --verbose`; the finding below appears.

```python
from openai import OpenAI

client = OpenAI(api_key="sk-proj-EXAMPLEnotARealKey0123456789abcdef")

def summarize(text: str) -> str:
    r = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": f"Summarize:\n{text}"}],
    )
    return r.choices[0].message.content
```

Checked with Keryn's browser engine when this page was built: it reports `vulnfix-ai-ai_hardcoded_provider_key` at line 3 (error, proof 1). The rule's own logic is not published, so it cannot run in this tab; the pack list in the [playground](https://keryn.dev/playground/) shows what does.

## vulnfix-ai-js_ai_eval_dynamic

`error` javascript, typescript mcp

CWE-95 (insecure-output-handling): dynamic eval()/new Function() on a non-literal value. In an LLM/agent/MCP context this runs model output or a tool argument as code (code injection). Avoid eval; parse data with JSON.parse.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-95](https://keryn.dev/rules/?cwe=CWE-95) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

Also reported under the older id `vulnfix-ai-ts_ai_eval_dynamic`.

## vulnfix-ai-js_ai_eval_parse_fallback

`error` javascript, typescript vulnfix-ai

CWE-94 (insecure-output-handling): eval()/new Function() is used as the fallback when JSON.parse fails on LLM/tool output. A value that could not be parsed as data is then executed as code — if it comes from an LLM, a request, or a file, this is code injection (the same shape as the confirmed CodeFuse-muAgent, Squrve, and DataArc-SynData-Toolkit RCEs).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

Also reported under the older id `vulnfix-ai-ts_ai_eval_parse_fallback`.

## vulnfix-ai-ai_mcp_js_tool_command

`error` javascript, typescript mcp

CWE-78 (mcp-tool-exposure): A JS/TS MCP tool handler reaches a shell/subprocess -- the model (or a malicious MCP client request) controls the handler's arguments.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-78](https://keryn.dev/taxonomies/cwe/#cwe-78-os-command-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

Also reported under the older id `vulnfix-ai-ts_ai_mcp_js_tool_command`.

## vulnfix-ai-ai_mcp_js_tool_path

`error` javascript, typescript mcp

CWE-22 (mcp-tool-exposure): A JS/TS MCP tool handler reads/writes a filesystem path built from its arguments (path traversal).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

Also reported under the older id `vulnfix-ai-ts_ai_mcp_js_tool_path`.

## vulnfix-ai-ai_hf_trust_remote_code

`error` python huggingface

CWE-94 (model-supply-chain): HuggingFace loads and executes arbitrary code from the model repo.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_torch_hub_load

`error` python pytorch

CWE-494 (model-supply-chain): Downloads and executes a remote repo's model code without integrity check.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-494](https://keryn.dev/taxonomies/cwe/#cwe-494-download-of-code-without-integrity-check) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_keras_load_model

`error` python keras

CWE-502 (model-supply-chain): Keras models can carry Lambda layers that execute arbitrary code on load.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_mlflow_load_model

`error` python mlflow

CWE-502 (model-supply-chain): Loading an MLflow pyfunc model can execute packaged code.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_lc_python_repl

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): Gives the LLM a Python interpreter — model output runs as code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_python_ast_repl

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): Gives the LLM a Python interpreter — model output runs as code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_shell_tool

`error` python vulnfix-ai

CWE-78 (insecure-agent-tool): Gives the LLM a shell — model output runs as shell commands.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-78](https://keryn.dev/taxonomies/cwe/#cwe-78-os-command-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_pal_chain

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): PAL executes LLM-generated Python to solve problems.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_pandas_agent

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): Pandas agent executes LLM-generated Python against the dataframe.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_spark_agent

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): Spark agent executes LLM-generated code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_llm_math

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): LLMMathChain has historically eval()'d LLM output.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_sql_database_chain

`error` python vulnfix-ai

CWE-89 (insecure-agent-tool): Executes LLM-generated SQL against the database.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-89](https://keryn.dev/taxonomies/cwe/#cwe-89-sql-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_bash_process

`error` python vulnfix-ai

CWE-78 (insecure-agent-tool): Runs LLM-provided commands through bash.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-78](https://keryn.dev/taxonomies/cwe/#cwe-78-os-command-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_requests_get_tool

`error` python vulnfix-ai

CWE-918 (insecure-agent-tool): Lets the agent issue arbitrary HTTP GETs (SSRF surface).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_autogen_local_executor

`error` python autogen

CWE-94 (insecure-agent-tool): AutoGen executes LLM-generated code locally with no sandbox.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication) [ASI10](https://keryn.dev/taxonomies/owasp-agentic/#asi10-rogue-agents)

## vulnfix-ai-ai_lc_python_repl_util

`error` python langchain

CWE-94 (insecure-agent-tool): The LangChain PythonREPL utility runs arbitrary Python.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_requests_post_tool

`error` python vulnfix-ai

CWE-918 (insecure-agent-tool): Lets the agent issue arbitrary HTTP POSTs (SSRF surface).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_requests_wrapper

`error` python vulnfix-ai

CWE-918 (insecure-agent-tool): Wraps arbitrary agent-driven HTTP requests (SSRF surface).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_cypher_chain

`error` python vulnfix-ai

CWE-943 (insecure-agent-tool): Executes LLM-generated Cypher against the graph database.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-943](https://keryn.dev/rules/?cwe=CWE-943) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_llamaindex_pandas_query

`error` python llamaindex, express

CWE-94 (insecure-agent-tool): LlamaIndex PandasQueryEngine eval()s LLM-generated pandas expressions.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_smolagents_code_agent

`error` python smolagents

CWE-94 (insecure-agent-tool): smolagents CodeAgent executes LLM-generated Python.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_python_interpreter_tool

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): A Python-interpreter tool runs LLM-generated code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_code_interpreter_tool

`error` python vulnfix-ai

CWE-94 (insecure-agent-tool): A code-interpreter tool runs LLM-generated code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_llamaindex_download_loader

`error` python llamaindex

CWE-494 (model-supply-chain): Downloads and executes a loader's code from llama-hub without integrity check.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-494](https://keryn.dev/taxonomies/cwe/#cwe-494-download-of-code-without-integrity-check) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_lc_file_mgmt_toolkit

`error` python vulnfix-ai

CWE-22 (excessive-agency): Grants the agent read/write/delete/move file tools.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_lc_write_file_tool

`error` python vulnfix-ai

CWE-22 (excessive-agency): Grants the agent a write-arbitrary-file tool.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_streamlit_unsafe_html

`error` python streamlit

CWE-79 (insecure-output-handling): Rendering (often LLM) output as HTML enables XSS; sanitize first.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-79](https://keryn.dev/taxonomies/cwe/#cwe-79-cross-site-scripting) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution)

## vulnfix-ai-ai_lc_allow_dangerous_code

`error` python vulnfix-ai

CWE-94 (unsafe-flag): Opts into executing LLM-generated code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_lc_allow_dangerous_deser

`error` python vulnfix-ai

CWE-502 (unsafe-flag): Opts into unpickling untrusted data (e.g. a downloaded FAISS index).

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_xxe_xmltodict_disable_entities

`error` python vulnfix-ai

CWE-611 (unsafe-flag): Explicitly re-enables XML external entity resolution (XXE) in xmltodict, which defaults to disabled -- a document-ingestion tool parsing this way can be made to read local files or reach internal network hosts via a crafted XML doctype.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing.

[CWE-611](https://keryn.dev/rules/?cwe=CWE-611) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_xxe_lxml_resolve_entities

`error` python vulnfix-ai

CWE-611 (unsafe-flag): An lxml XMLParser with resolve\_entities=True enables XXE -- a crafted XML document parsed this way can read local files or reach internal network hosts via a DOCTYPE external entity declaration.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing.

[CWE-611](https://keryn.dev/rules/?cwe=CWE-611) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_lc_allow_dangerous_requests

`error` python vulnfix-ai

CWE-918 (unsafe-flag): Opts into agent-driven HTTP requests (SSRF surface).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_crewai_allow_code_exec

`error` python crewai

CWE-94 (unsafe-flag): Opts a CrewAI agent into executing LLM-generated code.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication)

## vulnfix-ai-ai_codeexec_unsafe

`error` python vulnfix-ai

CWE-94 (unsafe-flag): Enables an interpreter/executor's unsafe (unsandboxed) mode.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution)

## vulnfix-ai-ai_langchain_load_secrets_env

`error` python langchain

CWE-502 (unsafe-flag): langchain load()/loads() with secrets\_from\_env=True lets a crafted 'lc' constructor payload pull values out of the process environment (API keys, tokens) during deserialization -- CVE-2025-68664/68665 lineage.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## vulnfix-ai-ai_gradio_share

`error` python gradio

CWE-668 (exposure): Publishes the app on a public gradio.live tunnel.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-668](https://keryn.dev/taxonomies/cwe/#cwe-668-exposure-of-resource-to-wrong-sphere) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse)

## vulnfix-ai-ai_mcp_sse_transport

`warning` python mcp

CWE-306 (exposure): MCP server exposed over the network (SSE); confirm auth/authorization on tool calls.

Confidence **P1**: dangerous in context. False-positive risk **high**: it finds a lead to confirm, so expect benign hits.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-306](https://keryn.dev/taxonomies/cwe/#cwe-306-missing-authentication-for-critical-function) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication)

## vulnfix-ai-ai_mcp_http_transport

`warning` python mcp

CWE-306 (exposure): MCP server exposed over the network (HTTP); confirm auth/authorization on tool calls.

Confidence **P1**: dangerous in context. False-positive risk **high**: it finds a lead to confirm, so expect benign hits.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-306](https://keryn.dev/taxonomies/cwe/#cwe-306-missing-authentication-for-critical-function) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_bind_all

`warning` python vulnfix-ai

CWE-306 (exposure): Server bound to all interfaces; confirm it is not reachable without auth.

Confidence **P1**: dangerous in context. False-positive risk **high**: it finds a lead to confirm, so expect benign hits.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-306](https://keryn.dev/taxonomies/cwe/#cwe-306-missing-authentication-for-critical-function) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication)

## vulnfix-ai-ai_cors_wildcard_creds

`error` python vulnfix-ai

CWE-942 (exposure): CORS allow\_origins=\* with allow\_credentials=True lets any site make credentialed requests to the AI API; scope origins to an allowlist.

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-942](https://keryn.dev/rules/?cwe=CWE-942) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse)

## vulnfix-ai-ai_mcp_tool_command

`error` python mcp

CWE-78 (mcp-tool-exposure): An MCP tool handler reaches a shell/subprocess — the model controls the args.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-78](https://keryn.dev/taxonomies/cwe/#cwe-78-os-command-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_tool_code_exec

`error` python mcp

CWE-94 (mcp-tool-exposure): An MCP tool handler reaches eval/exec — the model controls the args.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_tool_sql

`error` python mcp

CWE-89 (mcp-tool-exposure): An MCP tool handler executes SQL built from its arguments.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-89](https://keryn.dev/taxonomies/cwe/#cwe-89-sql-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_tool_ssrf

`error` python mcp

CWE-918 (mcp-tool-exposure): An MCP tool fetches a URL from its arguments (SSRF surface).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_tool_path_read

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool opens a filesystem path from its arguments (path traversal).

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_ssrf

`error` python mcp

CWE-918 (mcp-tool-exposure): An MCP tool passes an unvalidated argument straight to an HTTP fetch (SSRF). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reaches](https://keryn.dev/docs/edges/edge-kinds/#reaches) content or traffic gets to a thing; it crosses the [`user->prompt`](https://keryn.dev/docs/edges/trust-boundaries/#user-to-prompt) boundary (untrusted input reaching a prompt).

[CWE-918](https://keryn.dev/taxonomies/cwe/#cwe-918-server-side-request-forgery) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_path

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool opens an unvalidated argument as a filesystem path (traversal). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_command

`error` python mcp

CWE-78 (mcp-tool-exposure): An MCP tool passes an unvalidated argument to a shell/subprocess. The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-78](https://keryn.dev/taxonomies/cwe/#cwe-78-os-command-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_write

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool writes to an unvalidated path argument (arbitrary file write -&gt; often code execution via a config/startup/cron file). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_delete

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool deletes/removes an unvalidated path argument (destructive). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_eval

`error` python mcp

CWE-94 (mcp-tool-exposure): An MCP tool passes an unvalidated argument straight to eval/exec (code injection; the model or a prompt-injecting document controls the arg). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_nosql

`error` python mcp, mongodb

CWE-943 (mcp-tool-exposure): An MCP tool passes an unvalidated argument into a MongoDB $where clause (the operator takes a JS string the database evaluates -- NoSQL injection). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-943](https://keryn.dev/rules/?cwe=CWE-943) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_deser

`error` python pytorch, mcp

CWE-502 (mcp-tool-exposure): An MCP tool passes an unvalidated argument to an unsafe deserialize / model load (pickle / yaml.load / joblib / torch.load / FAISS) — arbitrary code runs on load. The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_ssti

`error` python mcp

CWE-1336 (mcp-tool-exposure): An MCP tool compiles an unvalidated argument as a template (SSTI -&gt; RCE via Jinja/Mako). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-1336](https://keryn.dev/rules/?cwe=CWE-1336) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_sql

`error` python mcp

CWE-89 (mcp-tool-exposure): An MCP tool passes an unvalidated argument as the entire SQL statement to execute() (SQL injection). The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-89](https://keryn.dev/taxonomies/cwe/#cwe-89-sql-injection) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_git_init

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool runs git init at an unvalidated path argument -- can turn any directory the process can write to (including \~/.ssh) into a git repository, the first step of the CVE-2025-68143 mcp-server-git RCE chain. The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_param_git_arg_injection

`error` python mcp

CWE-88 (mcp-tool-exposure): An MCP tool passes an unvalidated argument straight into GitPython's git-CLI proxy (repo.git.&lt;subcommand&gt;) -- a value starting with '-' is interpreted as a git flag, not data (e.g. '--output=/path' turns a read into a file write). CVE-2025-68144 lineage. The value comes directly from a tool parameter with no validation — reachable via the agent / prompt injection.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another.

[CWE-88](https://keryn.dev/rules/?cwe=CWE-88) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_torch_load_unsafe

`error` python pytorch

CWE-502 (model-supply-chain): torch.load without weights\_only=True unpickles arbitrary code from the checkpoint. Pass weights\_only=True (or load only trusted files).

Confidence **P1**: dangerous in context. False-positive risk **low**: an exact API or flag, so hits are almost always real.

Edge inspected: [depends_on](https://keryn.dev/docs/edges/edge-kinds/#depends-on) something relies on a component it does not verify; it crosses the [`supply-chain`](https://keryn.dev/docs/edges/trust-boundaries/#supply-chain) boundary (code, models or prompts pulled in from outside).

[CWE-502](https://keryn.dev/taxonomies/cwe/#cwe-502-deserialization-of-untrusted-data) [LLM03](https://keryn.dev/taxonomies/owasp-llm/#llm03-supply-chain) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities) [ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning)

## vulnfix-ai-ai_eval_parse_fallback

`error` python vulnfix-ai

CWE-94 (insecure-output-handling): eval()/exec() is used as the fallback when a structured parse (json.loads / json.load) fails. A value that could not be parsed as data is then executed as code — if it comes from an LLM, a request, or a file, this is code injection (the CodeFuse-muAgent RCE had this exact shape). Use ast.literal\_eval or reject on parse failure.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [calls](https://keryn.dev/docs/edges/edge-kinds/#calls) one thing invokes another; it crosses the [`model->code`](https://keryn.dev/docs/edges/trust-boundaries/#model-to-code) boundary (model output reaching code, a shell, a query or a page).

[CWE-94](https://keryn.dev/taxonomies/cwe/#cwe-94-code-injection) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_mcp_tool_unsafe_output_dir

`error` python mcp

CWE-22 (mcp-tool-exposure): An MCP tool accepts an optional output-directory/path parameter with a safe-looking default, but only applies that default when the caller omits the value entirely -- when a caller DOES supply one, it is used with no containment check (no Path(...).resolve() + is\_relative\_to(base), commonpath, or startswith-base check against any base directory), so an absolute or ../-escaping value writes outside the intended directory. Generalized from 3 independently-found instances in one session (fengin/image-gen-server, SkyworkAI/Mureka-mcp, hiteshK03/davinci-resolve-mcp) -- verify by hand that no containment check exists anywhere in the function before confirming; this rule is a syntactic approximation, not a dataflow proof.

Confidence **P1**: dangerous in context. False-positive risk **medium**: the pattern is legitimate in many programs, so check each hit.

Edge inspected: [reads](https://keryn.dev/docs/edges/edge-kinds/#reads) one thing reads from another.

[CWE-22](https://keryn.dev/taxonomies/cwe/#cwe-22-path-traversal) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## vulnfix-ai-ai_route_no_auth_dependency

`warning` python mcp

CWE-306 (mcp-tool-exposure): an HTTP route reaching a dangerous capability (shell/eval/SQL) has no per-route auth dependency visible in its signature. This is a noisy, cross-reference-only signal -- auth applied via middleware or a global dependency is invisible to this syntax-only check, so do NOT triage this rule's hits individually. It exists to be joined (by auth\_crossref.py) against other findings in the same file: a by-design/weak dangerous-capability finding becomes worth a second look when nothing in the same file appears to gate who can reach it.

Confidence **P1**: dangerous in context. False-positive risk **high**: it finds a lead to confirm, so expect benign hits.

Edge inspected: [grants](https://keryn.dev/docs/edges/edge-kinds/#grants) authority is given or left unchecked.

[CWE-306](https://keryn.dev/taxonomies/cwe/#cwe-306-missing-authentication-for-critical-function) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [ASI05](https://keryn.dev/taxonomies/owasp-agentic/#asi05-unexpected-code-execution) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)
