shannon
Warn
Audited by Snyk on Apr 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The Analogist teammate prompt explicitly instructs the agent to "Use WebSearch if needed to find solved problems in the same domain," which directs the skill at runtime to fetch and interpret open/public web content (untrusted third‑party sources) and use those findings to influence analogies and solution decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata