orchestrate

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

• Third-party content exposure detected (high risk: 0.90). The skill's Research Agent prompt and Pattern A explicitly instruct agents to use WebSearch and WebFetch to pull blog posts, GitHub repos, and other web docs (e.g., "Use WebSearch and WebFetch to get current docs" in the Research template), so the agent will ingest untrusted public web content that can materially influence research, design, and orchestration decisions.