receiving-code-review

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

• Third-party content exposure detected (high risk: 0.75). The skill’s required workflow is to respond to “code review feedback,” which at runtime would typically ingest outsider-authored free-form text from external review comments/threads (e.g., GitHub PR review comments) into the agent’s LLM context via the platform’s comment-body text.