ideation
Warn
Audited by Snyk on Aug 10, 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 Mode B (Pipeline) the skill ingests the user’s free-form “brain dump” from the Intake phase (“Accept whatever the user provides…”) and then uses it to generate contract/PRD/spec artifacts, so outsider-authored text is directly consumed at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata