ia-receiving-code-review

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is to process PR review comments (including “external reviewers (PR comments, open source)”) and read prior review threads via the GitHub API, so outsider-authored free-form comment bodies can be ingested into the agent’s LLM context at runtime.