coderabbit-resolver

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses user-generated GitHub PR review threads and issue comments via gh api (see workflows/review-loop.md Step 1a and scripts/check-ci-status.sh / wait-for-ratelimit.sh and references/github-graphql-api.md), and those untrusted comment bodies are read and used to decide waits, posts, thread resolution, and whether to merge — allowing third-party content to materially alter agent behavior.