ops-triage

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests public/user-generated content (GitHub issues via gh CLI, Sentry via sentry-cli/API, Linear GraphQL, and WebFetch/WebSearch) as part of its triage workflow and uses that content to make actions (auto-resolve, dispatch agents, close issues), so third-party content could influence agent behavior.