gws-modelarmor-sanitize-response
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
gwscommand-line utility to perform security sanitization of model outputs. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from model responses, which presents an indirect prompt injection surface.
- Ingestion points: Untrusted text is passed to the tool via the
--textflag or standard input inSKILL.md. - Boundary markers: No explicit boundary markers or delimiters are used in the command-line examples to isolate the untrusted content.
- Capability inventory: The skill relies on the
gwsbinary for all operations as specified inSKILL.md. - Sanitization: The primary purpose of the skill is to sanitize data using established Model Armor templates, providing a defensive layer against prompt injection.
Audit Metadata