eval-rubric-format-structure
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of descriptive text and markdown tables defining evaluation criteria for legal documents. It does not contain any executable scripts, shell commands, or tool invocations.
- [SAFE]: No evidence of prompt injection or attempts to override AI safety guidelines was found. The language is purely instructional for evaluation purposes.
- [SAFE]: All external references, including the GitHub repository link in the metadata, point to the author's own project and are provided for documentation and source attribution rather than automated downloading or execution.
Audit Metadata