# inventory-aibom-v1

> inventory-aibom-v1: 29 Keryn rules for generic (29 info).

Source: https://keryn.dev/rules/inventory-aibom-v1/

29 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.

## keryn.inv.lib.openai

`info` generic openai

References the OpenAI SDK.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.anthropic

`info` generic anthropic

References the Anthropic SDK.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.google-genai

`info` generic google

References a Google generative-AI SDK.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.langchain

`info` generic langchain

References LangChain.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.langgraph

`info` generic langgraph

References LangGraph.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.llamaindex

`info` generic llamaindex

References LlamaIndex.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.vercel-ai

`info` generic vercel-ai-sdk

References the Vercel AI SDK.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.huggingface

`info` generic huggingface

References Hugging Face transformers/hub.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.ollama

`info` generic ollama

References Ollama.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.litellm

`info` generic litellm

References LiteLLM gateway.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.crewai-autogen

`info` generic crewai, autogen

References a multi-agent framework.

Confidence **P1**: dangerous in context.

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).

[ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication)

## keryn.inv.vectordb

`info` generic inventory-aibom

References a vector database client.

Confidence **P1**: dangerous in context.

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).

[ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning)

## keryn.inv.mcp

`info` generic mcp

References the Model Context Protocol SDK or a FastMCP server.

Confidence **P1**: dangerous in context.

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).

[ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## keryn.inv.guardrail

`info` generic inventory-aibom

References an LLM guardrail/injection-defence library.

Confidence **P1**: dangerous in context.

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).

[ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack)

## keryn.inv.model.openai

`info` generic openai

Hard-coded OpenAI model identifier.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.model.anthropic

`info` generic anthropic

Hard-coded Anthropic model identifier.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.model.google

`info` generic google

Hard-coded Gemini model identifier.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.model.open-weights

`info` generic inventory-aibom

Hard-coded open-weights model identifier.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.service.endpoint

`info` generic inventory-aibom

References a hosted LLM API endpoint.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.remote-code-model

`info` generic inventory-aibom

Model loaded with trust\_remote\_code enabled.

Confidence **P1**: dangerous in context.

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).

[ASI04](https://keryn.dev/taxonomies/owasp-agentic/#asi04-agentic-supply-chain-vulnerabilities)

## keryn.inv.lib.openai.manifest

`info` generic openai, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.anthropic.manifest

`info` generic anthropic, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.litellm.manifest

`info` generic litellm, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.langchain.manifest

`info` generic langchain, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.langgraph.manifest

`info` generic langgraph, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.lib.huggingface.manifest

`info` generic huggingface, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.mcp.manifest

`info` generic mcp, browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

[ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## keryn.inv.guardrail.manifest

`info` generic browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

## keryn.inv.vectordb.manifest

`info` generic browser-extension

Declared in a Python project manifest.

Confidence **P1**: dangerous in context.

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).

[ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning)
