prd-to-plan
Warn
Audited by Snyk on Aug 25, 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 prd-to-plan’s required runtime workflow, the agent “read and internalise the PRD” from either a file in
.agents/docs/or a referenced GitHub issue, meaning outsider-authored PRD text can be ingested during planning without selecting a specific predetermined safe item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata