think

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Phase 1.5 ("Search Before Building") in think/references/search-before-building.md requires the agent to search public sources (tools, packages, open issues and PRs, forums) and "report what you found" before the diagnostic, meaning the agent will fetch and interpret untrusted, user-generated third‑party content as part of its workflow.