graphrag-evaluation
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is purely informational, providing methodology, guidelines, and templates for evaluating GraphRAG system quality. It does not contain any functional logic that could be exploited.
- [NO_CODE]: There are no scripts (Python, Javascript, Shell) or configuration files that trigger code execution. The files are restricted to documentation (Markdown) and a static data structure (JSON).
- [EXTERNAL_DOWNLOADS]: No external URLs are used for fetching data or code. All resources are local to the skill package.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive system paths.
Audit Metadata