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 ingests GitHub-hosted, user-generated CI content (e.g., via "gh pr checks", "gh run view --log", and "gh api /repos/.../actions/jobs/.../logs" as shown in SKILL.md and scripts/inspect_pr_checks.py) and then summarizes those logs to create and execute fix plans, so untrusted third-party log content can materially influence decisions and actions.