openapi-generator

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted source code and JSDoc comments to generate API documentation. This creates a surface where external data enters the agent's context.\n
  • Ingestion points: The scripts read local project files and parse them using Babel and TypeScript compilers to extract route and schema information.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are included in the extraction logic.\n
  • Capability inventory: The skill uses fs for reading source files and writing the output specification, and commander for CLI interaction.\n
  • Sanitization: The tool relies on structured AST parsing to interpret code, which inherently structures the data but does not sanitize text content within comments.\n- [SAFE]: All libraries, file system operations, and code patterns are consistent with the skill's stated purpose of API documentation generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:14 PM
Security Audit — agent-trust-hub — openapi-generator