api-documentation-sync
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process untrusted external data, specifically the project's source code and existing API specifications, to generate or validate documentation. This creates a surface where malicious instructions embedded in the code (e.g., in comments or handler names) could influence agent behavior.
- Ingestion points: The skill reads various project source files (Express, NestJS, FastAPI, etc.) and OpenAPI/Swagger specification files (YAML/JSON) during Phase 1 (Discovery) and Phase 2 (Strategy).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to prevent the agent from accidentally executing instructions found within the code comments or strings it analyzes.
- Capability inventory: The agent has the capability to read files from the filesystem and write the results to a documentation file (
openapi.yamloropenapi.json). - Sanitization: There is no mention of sanitization, filtering, or validation of the extracted strings (such as handler names or descriptions) before they are incorporated into the final documentation output.
Audit Metadata