api-doc-generator

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it processes external data that is later reflected in the agent's context.
  • Ingestion points: The scripts/generate_docs.py script ingests untrusted data from OpenAPI/OAS specification files (YAML/JSON).
  • Boundary markers: The generated markdown documentation lacks boundary markers or instructions to the agent to treat content from the specification as untrusted data.
  • Capability inventory: The skill can perform file system operations, specifically creating directories and writing multiple markdown files.
  • Sanitization: The script interpolates content from the specification fields (such as description, summary, and example) directly into markdown files without sanitization or escaping.
  • [SAFE]: The script uses yaml.safe_load() for parsing specification files, which is a security best practice that prevents arbitrary code execution during YAML deserialization.
  • [SAFE]: The skill performs local file operations (reading a spec and writing documentation) that are consistent with its stated purpose as an API documentation generator.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 12:40 AM
Security Audit — agent-trust-hub — api-doc-generator