coderabbit-migration-deep-dive

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md includes bash/gh API calls (e.g., Step 1 and Step 6 "gh api" queries of org installations, repo contents, PRs, and reviews) that fetch user-generated GitHub repository and PR data which the workflow reads and uses to drive migration decisions, so it exposes the agent to untrusted third-party content that could inject instructions indirectly.