gh-fix-ci

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 inspects live GitHub PR/check data and GitHub Actions run/job logs (see SKILL.md steps 3–4 and scripts/inspect_pr_checks.py: fetch_checks, fetch_run_log, fetch_job_log, analyze_check), and the agent parses those user-generated logs to summarize failures and drive fix decisions, which could allow indirect prompt-injection via untrusted CI log content.