gws-modelarmor-sanitize-response

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or security vulnerabilities were detected. The skill serves a defensive purpose by providing a mechanism to filter model outputs for safety.\n- [COMMAND_EXECUTION]: The skill utilizes the gws binary to perform content sanitization. This execution is consistent with the stated purpose of the skill and is triggered by explicit user commands.\n- [SAFE]: The skill references a shared configuration file (../gws-shared/SKILL.md) for authentication and global flags, which is a standard practice for managing access to cloud services securely.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 04:56 PM