analyze-test-run
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [Automated External Downloads]: The skill downloads test artifacts (JUnit XML and Markdown reports) from GitHub Actions using official MCP tools. While it fetches outside content, it is scoped strictly to the 'microsoft/GitHub-Copilot-for-Azure' repository and follows secure practices by using job logs as a fallback if network restrictions apply.- [Automated Issue Creation]: The skill can automatically create GitHub issues for test failures. This is the intended primary purpose of the skill and includes a search step to prevent duplicate issue creation. The tool calls are restricted to the vendor's own repository.- [Log Analysis Surface]: The skill processes untrusted test output data (JUnit XML and agent metadata) to determine root causes. While this represents a potential surface for indirect prompt injection, the skill includes logic to classify failures into predefined categories (Timeout, Quota, etc.) and uses structured reporting templates, which mitigates the risk of the agent being misdirected by test failure strings.
Audit Metadata