brainstorm

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's required "Phase 1: Research First" in SKILL.md explicitly directs the agent to generate web searches and synthesize findings from existing solutions/best practices on the open web, meaning it will ingest untrusted public third-party content that can materially influence choices and actions.