diagnose-ci-failures

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (SKILL.md steps 2–3) explicitly uses GitHub CLI commands like "gh pr view ... --json statusCheckRollup" and "gh run view --log-failed" to fetch PR details and CI logs (user-generated, third-party content) which the agent must read and use to generate a remediation plan, so untrusted content can influence decisions.