niuma-help
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and documentation for a product's help system. It does not perform any executable actions, shell commands, or network requests.
- [SAFE]: No prompt injection or behavior override attempts were found in the instructions. The role-play is limited to acting as a 'Product Usage Consultant'.
- [SAFE]: No external dependencies, scripts, or remote code patterns are present in the skill files.
- [SAFE]: While the documentation mentions features like 'API Keys' and 'Terminal Commands', these are descriptions of the application's functionality for the user and do not represent the skill itself accessing sensitive data or executing unsafe commands.
Audit Metadata