design-critique
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill's conditional "~~user feedback" connector path tells the agent to cross-reference recent user feedback and support tickets, which are outsider-submitted free text read from a feed without the agent selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata