sub-agent-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly exposes WebFetch/WebSearch in the Available Tools Reference and directs research agents and prompt templates to "Check official documentation at [URL pattern or search]" and to consult community resources (e.g., GitHub, blogs), so agents are expected to fetch and interpret open public third‑party content.