mise-en-place
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The workflow's "Research (Web)" step explicitly instructs the agent to run targeted web research and "capture sources in prd.json," meaning the agent will fetch and read open/public third‑party web content as part of its workflow.
Audit Metadata