gws-modelarmor-sanitize-prompt
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
gwsCLI tool to perform prompt sanitization. This is the primary and intended function of the skill, utilizing a tool specified in the metadata requirements. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input via the
--textflag or standard input. However, its explicit purpose is to pass this data to a security service (Model Armor) for sanitization, which serves as a defensive measure against prompt injection and other content risks.
Audit Metadata