wafr-facilitator
Warn
Audited by Snyk on Aug 18, 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 skill ingests outsider-authored free text directly from the facilitator/user chat messages (e.g., the architecture “text description” and any mid-session customer statements) via the conversational prompt that drives Step 1–Step 4 generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata