recipe-validate
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md mandates “Market Research (for Value/Viability validation)” using “Web search,” which at runtime can fetch public web content and inject that outsider-authored free text into the LLM context via the browsing/search results (plus potential “prototype generation” reading design blueprint artifacts that may be user-supplied but are not guaranteed to be non-outsider).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata