clarify
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow tells the agent to drop readings "a source in reach rules out," an unspecified lookup that could reach arbitrary outsider-authored web content, but the skill names no feed or service and the agent must choose to fetch anything.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata