parallel-ci-triage

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest CI logs via the GitHub CLI (e.g., gh run view --job <JOB_ID> --log) or paste logs from the GitHub Actions UI, so it will read untrusted, user-generated third-party content (CI logs) that can influence troubleshooting actions and tool use.