brainstorming-pm
Warn
Audited by Snyk on Mar 1, 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). The skill's Stage 2 "Parallel Perspective Generation" explicitly instructs Task agents to "Conduct 1-2 WebSearch queries to support your analysis" (SKILL.md Stage 2), meaning the orchestrator ingests and acts on open/public web content returned by those agents and uses it in downstream convergence and handoff decisions.
Audit Metadata