dependency-auditor
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted manifest files from analyzed projects, which constitutes an indirect prompt injection surface.\n
- Ingestion points: Manifest and lockfiles (e.g., package.json, requirements.txt, go.mod) are ingested by dep_scanner.py, license_checker.py, and upgrade_planner.py.\n
- Boundary markers: No explicit delimiters or instructions are used to distinguish untrusted dependency data from the tool's generated report structure.\n
- Capability inventory: The scripts perform local file system reads and can write reports to the file system using the --output flag.\n
- Sanitization: No specific sanitization or escaping of extracted dependency metadata (such as package names or versions) is performed before it is included in the output reports.
Audit Metadata