evidence-synthesis-ai
Warn
Audited by Snyk on Apr 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). SKILL.md explicitly requires pulling and reading studies from public third‑party sources (e.g., "pulling relevant studies from PubMed, Cochrane CENTRAL, WHO ICTRP, and published clinical practice guidelines" and example steps to "Search PubMed and Cochrane"), so the agent ingests external public content that can materially influence its synthesis and downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata