constraints-extractor
Warn
Audited by Snyk on Aug 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required runtime workflow ingests any repository documentation files it auto-discovers (e.g., docs/, README.md, SECURITY.md, COMPLIANCE.md, ARCHITECTURE.md, AGENTS.md/CLAUDE.md, and an existing CONSTRAINTS.md) by reading each assigned file in full for per-document extraction, meaning outsider-authored text can be submitted via those repository files into the scan set.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata