gh-fix-ci

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

• Third-party content exposure detected (high risk: 0.75). The skill runs scripts/inspect_pr_checks.py, which uses gh run view <run_id> --log and gh api .../actions/jobs/<job_id>/logs to ingest GitHub Actions log text (outsider-authored build output from other contributors/workflows) into the LLM context via the produced failure snippets.