new-issue
Warn
Audited by Snyk on Jul 28, 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). In SKILL.md the runtime workflow includes searching titles and full text for duplicates and then using the complete supplied body verbatim (step 3 and step 4), which implies the agent ingests user/outsider-authored free text from an external source it is searching.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata