gws-modelarmor-sanitize-response
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'gws' command-line interface to interact with Google Model Armor services. This is the core functionality intended by the 'googleworkspace' author for sanitizing model outputs.
- [SAFE]: No indicators of prompt injection, data exfiltration, or obfuscation were found. The skill is focused on enhancing security through content filtering.
- [SAFE]: The 'gws' binary is a platform-specific requirement listed in the metadata and is consistent with the author's identity.
Audit Metadata