github-code-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-generated PR data and repository contents from third-party GitHub sources (e.g., "curl https://api.github.com/repos/.../pulls/$PR_NUMBER", "curl .../pulls/$PR_NUMBER/files", and "git fetch origin pull/$PR_NUMBER/head:pr-$PR_NUMBER") and the agent is expected to read and act on those PR bodies and file contents as part of its review workflow, so untrusted third-party content can influence its decisions and tool usage.