research
Warn
Audited by Snyk on Mar 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "search multiple sources," "read the actual source," and rely on "community answers," which requires fetching and interpreting content from public, user-generated third‑party websites and forums as part of its workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata