threat-modeling
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). The threat-modeling skill ingests the user’s provided system design/architecture/codebase context (directly via $ARGUMENTS/user prompt) and uses it as free text for analysis, making it susceptible to indirect prompt injection from outsider-authored content in those documents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata