# graphql-ai-boundary-v2

> graphql-ai-boundary-v2: 6 Keryn rules for typescript, javascript, python (4 warning, 2 info).

Source: https://keryn.dev/rules/graphql-ai-boundary-v2/

6 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.

## seceng.graphql.ai-mutation-without-auth-context

`warning` typescript, javascript graphql

GraphQL resolver or mutation performs an AI/tool call without visible authorization from context.

Confidence **P2**: a heuristic or a posture check: confirm by reading the code. 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-306](https://keryn.dev/taxonomies/cwe/#cwe-306-missing-authentication-for-critical-function) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [LLM10](https://keryn.dev/taxonomies/owasp-llm/#llm10-unbounded-consumption) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI08](https://keryn.dev/taxonomies/owasp-agentic/#asi08-cascading-failures)

## seceng.graphql-args-direct-to-llm

`warning` typescript, javascript, python graphql

GraphQL args are passed directly into LLM prompt/messages without visible validation. This can expose a prompt injection path.

Confidence **P2**: a heuristic or a posture check: confirm by reading the code. 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-20](https://keryn.dev/taxonomies/cwe/#cwe-20-improper-input-validation) [LLM01](https://keryn.dev/taxonomies/owasp-llm/#llm01-prompt-injection) [ASI01](https://keryn.dev/taxonomies/owasp-agentic/#asi01-agent-goal-hijack)

## seceng.graphql-resolver-id-from-args-without-owner

`warning` typescript, javascript, python graphql

GraphQL resolver uses args.id/userId/tenantId to load AI resources without visible context ownership binding.

Confidence **P2**: a heuristic or a posture check: confirm by reading the code. 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-639](https://keryn.dev/taxonomies/cwe/#cwe-639-authorization-bypass-through-user-controlled-key) [LLM06](https://keryn.dev/taxonomies/owasp-llm/#llm06-excessive-agency) [LLM08](https://keryn.dev/taxonomies/owasp-llm/#llm08-vector-and-embedding-weaknesses) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation) [ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning)

## seceng.graphql-schema-exposes-prompt-or-tool-types

`warning` typescript, javascript, python graphql

GraphQL schema exposes prompt, system instruction, tool schema, scratchpad, or memory fields.

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-200](https://keryn.dev/taxonomies/cwe/#cwe-200-exposure-of-sensitive-information-to-an-unauthorized-actor) [LLM02](https://keryn.dev/taxonomies/owasp-llm/#llm02-sensitive-information-disclosure) [LLM07](https://keryn.dev/taxonomies/owasp-llm/#llm07-system-prompt-leakage) [ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## seceng.graphql-introspection-enabled-with-ai-schema

`info` typescript, javascript, python graphql

GraphQL introspection appears enabled while AI prompt/tool/memory schema fields are present. This can aid prompt or tool extraction.

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-200](https://keryn.dev/taxonomies/cwe/#cwe-200-exposure-of-sensitive-information-to-an-unauthorized-actor) [LLM07](https://keryn.dev/taxonomies/owasp-llm/#llm07-system-prompt-leakage) [ASI06](https://keryn.dev/taxonomies/owasp-agentic/#asi06-memory-and-context-poisoning) [ASI02](https://keryn.dev/taxonomies/owasp-agentic/#asi02-tool-misuse-and-exploitation)

## seceng.graphql-subscription-streams-llm-output

`info` typescript, javascript, python graphql

GraphQL subscription appears to stream LLM output without visible moderation or authorization control.

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

Edge inspected: [sends](https://keryn.dev/docs/edges/edge-kinds/#sends) data leaves for another party.

[CWE-1426](https://keryn.dev/rules/?cwe=CWE-1426) [LLM05](https://keryn.dev/taxonomies/owasp-llm/#llm05-improper-output-handling) [LLM10](https://keryn.dev/taxonomies/owasp-llm/#llm10-unbounded-consumption) [ASI03](https://keryn.dev/taxonomies/owasp-agentic/#asi03-identity-and-privilege-abuse) [ASI07](https://keryn.dev/taxonomies/owasp-agentic/#asi07-insecure-inter-agent-communication) [ASI08](https://keryn.dev/taxonomies/owasp-agentic/#asi08-cascading-failures)

Also reported under the older id `seceng.stream.graphql-subscription-llm-output-no-filter`.
