analyze-ci-failures
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The workflow explicitly fetches PR details and GitHub Action job logs from PRs using GitHub MCP tools (see "Gather information" and calls like github-mcp-server-get_job_logs and azure-sdk-mcp-azsdk_analyze_pipeline), which are untrusted, user-authored third-party content that the agent reads and uses to determine fixes and post comments.
Audit Metadata