openvmm-ci-investigation

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow runs python3 repo_support/investigate_ci.py, which resolves a PR to its failed CI runs and then downloads and parses JUnit XML and *-vmm-tests-logs (including petri.jsonl / petri.log content) from the CI artifacts, which are derived from outsider-authored PRs.