iteration-close
Warn
Audited by Snyk on Aug 26, 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). SKILL.md Phase 1 instructs the agent to “sweep this iteration's chat-born decisions” by reading/ingesting those chat decisions at runtime and banking them into tracked repo files before deletion, which can include outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata