prd-reviewing
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). This skill’s required workflow is to “Read the entire PRD” (Step 1) and then evaluate its sections, so at runtime it will ingest the PRD’s free-form text authored by someone other than the operating user (outsider PRD author) into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata