route-to-openapi

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill acts as a local documentation generator and does not perform any network operations or execute external code.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading external source code to generate documentation.
  • Ingestion points: Reads source code files (Python, JavaScript, Go) from the user-provided directory in scripts/generate_api_doc.py.
  • Boundary markers: Output is delimited within a structured JSON or YAML OpenAPI specification.
  • Capability inventory: Limited to file system reading of source files and writing the resulting specification to a local file or standard output. No subprocess execution or network access is present.
  • Sanitization: Extracted docstrings and comments are placed directly into the specification without filtering for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:12 AM