jaan-issue-solve

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests public, user-generated GitHub issue bodies and comments via the gh issue view ... --json body,comments step (Phase 1 Step 5) and uses that untrusted content to decide eligibility (skip/post) and to draft/post follow-up comments, so third-party content can influence the agent's actions and outputs.