adding-api-docs
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to ingest and analyze source code files, route handlers, and JSDoc annotations to generate documentation. This constitutes an attack surface where instructions embedded in processed data could influence agent behavior.
- Ingestion points: API route handlers and source code files (SKILL.md).
- Boundary markers: No boundary markers or "ignore embedded instructions" warnings are defined to protect the agent during code analysis.
- Capability inventory: File system access, package installation (npm install), and code generation.
- Sanitization: No explicit sanitization or validation of the content extracted from route handlers is described.
Audit Metadata