ln-911-github-triager

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 "Fetch Data" explicitly runs gh commands and a GraphQL query to load open GitHub issues, PRs, and discussions (user-generated content from public GitHub) which the agent parses in Phases 2–5 and uses to drive classifications and recommended actions, exposing it to untrusted third-party content.