gh-mcp

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow exposes GitHub read tools (e.g., pull_request_read, issue_read, get_job_logs, get_file_contents) whose inputs/returned text can include outsider-authored PR/issue bodies, comments, review text, and CI logs that are explicitly treated as untrusted data.