receiving-code-review

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text is likely ingested when the skill processes “External Reviewers” feedback (e.g., GitHub issue/PR review comments or inline review comment bodies) and then uses that text to generate the agent’s response; this is runtime LLM context from third-party authored messages.