ai-inventory
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted local project files to generate analysis reports.
- Ingestion points: The skill reads requirements.txt, setup.py, and pyproject.toml files from the local project path.
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore malicious instructions potentially embedded in the scanned files.
- Capability inventory: The skill utilizes Read, Write, Bash, Grep, and mcp_snyk_snyk_aibom tools.
- Sanitization: No input validation or sanitization of the extracted data is performed before it is presented in the final report.
Audit Metadata