to-prd
Warn
Audited by Snyk on Aug 12, 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
to-prdworkflow ingests the supplied “conversation” text (and repository context it is given) at runtime and then synthesizes it into a PRD for publishing, meaning outsiders who can post to that conversation can inject free text into the LLM input path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata