design-critic-loop
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 workflow reads outsider-authored free text supplied by the user during Phase 0 (the brief and references, potentially including user-provided URLs/images) via the “AskUserQuestion…request examples” elicitation gate and then passes that text into subagent critics.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata