openapi-generator

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow and provides code for scanning API route definitions and JSDoc comments from a project's source code to build a specification. This creates a surface where malicious instructions could be embedded in the analyzed code.
  • Ingestion points: The scanExpressWithOpenAPI function and the Babel-based traversal logic ingest data from a user-specified source directory (SKILL.md).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are provided in the route scanning or type conversion logic.
  • Capability inventory: The CLI script template includes file-system write access via fs.writeFileSync to save the generated documentation (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering for the strings extracted from route metadata or JSDoc comments before they are included in the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:31 AM
Security Audit — agent-trust-hub — openapi-generator