prd-task-creator
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Step 3 says to read/search existing GitHub issues (“gh issue list --search …” and “Read relevant architecture docs in
.agents/memory/”), so at runtime the workflow can ingest outsider-authored issue text or comments into the agent’s LLM context for PRD generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata