fact-check
Warn
Audited by Snyk on Aug 23, 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 describes a “事实核查” agent that requires “联网核查” the user-pasted claim at runtime, meaning outsider-authored free text (the user’s statement to check) is ingested directly into the workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata