review

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly reads and acts on user-generated GitHub PR content (PR body and bot/user review comments via gh api in Step 1.5 and Step 2.5 / greptile-triage) and uses those inputs to classify findings, decide fixes, and post replies, so untrusted third-party text can materially influence agent actions.