diagnosing-ci-and-merge-bottlenecks
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process external data from GitHub repositories, creating a surface for potential indirect prompt injection from pull request metadata or workflow descriptions.
- Ingestion points: Data is ingested via MCP tools
pull-requests,workflow-health,pr-lifecycle, andengineering-analytics-flaky-testsas described inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands within the GitHub data.
- Capability inventory: The skill's defined tools are restricted to reading and aggregating pipeline metrics; it lacks capabilities for writing to the file system or initiating outbound network requests for the processed data.
- Sanitization: No explicit sanitization or validation of the external content is performed before processing.
Audit Metadata