think

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

• Third-party content exposure detected (high risk: 0.80). The skill's required Phase 1.5 "Search Before Building" (see think/references/search-before-building.md and "Phase 1.5: Search Before Building" in SKILL.md) mandates searching public sites, repos, issues and forums for prior art and instructs the agent to read and use those findings before the diagnostic, which clearly ingests untrusted, user-generated third‑party content that can materially influence subsequent decisions and actions.