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's required workflow and script (SKILL.md step 4 and scripts/inspect_pr_checks.py) explicitly fetch and parse GitHub Actions run/job logs using "gh run view --log" and "gh api /repos/.../actions/jobs/<job_id>/logs", and those untrusted, user-generated CI log contents are interpreted to extract failure snippets and drive reproduction/fix decisions, so they could carry indirect prompt-injection content.