review

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via Greptile comment bodies fetched at runtime from GitHub PR/issue comments (gh api repos/$REPO/pulls/$PR_NUMBER/comments and gh api repos/$REPO/issues/$PR_NUMBER/comments), which are then read/processed by the agent for review findings.