coderabbit-enterprise-rbac

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and acts on repository-level configuration and user-generated content from GitHub (e.g., .github/.coderabbit.yaml and per-repo .coderabbit.yaml path_instructions, plus PRs/reviews fetched via the gh API in the audit script), which are untrusted third-party inputs that the agent interprets to control review behavior and actions.