release-analysis
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md Phase 5b (“Docs reconciliation”) requires reading in-tree runbooks/docs (which are outsider-authored if the operating user didn’t author them) and then uses their contents to drive LLM-based
doc-claim-validatorvalidation, so free-form runbook text can enter the agent context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata