api-recon-and-docs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from target API environments, creating an inherent surface for indirect prompt injection. 1. Ingestion points: Target JavaScript files (app.js) and API documentation paths (e.g., /swagger.json, /openapi.json) as described in the Recon Checklist. 2. Boundary markers: No explicit delimiters or boundary markers are defined in the instructions. 3. Capability inventory: The skill utilizes network read operations via curl. 4. Sanitization: No sanitization or validation of external content is specified.
- [SAFE]: The reconnaissance commands and common paths provided are industry-standard techniques for security auditing and documentation review.
Audit Metadata