cross-pollination

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

• Third-party content exposure detected (high risk: 1.00). This skill's workflow explicitly directs using public code search (e.g., grep.app at https://grep.app/search) to fetch and evaluate matches from open repositories, requiring the agent to read untrusted, user-generated code that can directly influence triage, PoC creation, and submission actions.