software-architecture-analysis
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md’s required workflow requires “Clone the target repository” and then “Read the top 15-25 files” (plus PHILOSOPHY/README and other repository files), which means outsider-authored free text from an arbitrary target GitHub repo is ingested into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata