gws-modelarmor
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: Analysis of the skill instructions and metadata revealed no evidence of malicious behavior, obfuscation, or unauthorized data exfiltration.
- [COMMAND_EXECUTION]: The skill relies on the 'gws' command-line tool to perform its primary function of content safety filtering. This tool is a documented requirement and its use is consistent with the skill's stated purpose.
Audit Metadata