analyze-test-run

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

• Third-party content exposure detected (high risk: 0.90). This skill downloads and parses GitHub Actions artifact ZIPs (temporary URLs) for owner "microsoft", repo "GitHub-Copilot-for-Azure" and explicitly reads SKILL-REPORT.md and agent-metadata-*.md from those artifacts to drive root-cause analysis and create GitHub issues, so untrusted/user-generated artifact content can materially influence the agent's decisions and actions.