code-reviewer

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime review workflow necessarily ingests the target project’s source files (e.g., PR/issue/codebase text provided by the operating user’s request), which are outsider-authored free-form text when reviewing third-party repositories or contributions; that text is then included in the agent’s LLM context for analysis.