code-review-ai-ai-review

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow ingests PR diff / PR description / static-analysis results into the LLM prompt (e.g., **Change Summary:** {pr_description} and **Modified Code:** {code_diff} in the AI-Assisted Review prompt), and those texts are outsider-authored free-form content from other contributors to the pull request.