gws-modelarmor-sanitize-response

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the 'gws' command-line binary to perform sanitization tasks. This binary is a vendor-provided tool required for the skill's operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes untrusted model output for sanitization.
  • Ingestion points: Data is accepted via the '--text' and '--json' command-line flags, or through standard input (stdin).
  • Boundary markers: No specific boundary markers are defined in the command structure, as the skill itself acts as the security boundary.
  • Capability inventory: The skill executes the 'gws' binary through a shell environment.
  • Sanitization: The primary function of this skill is to provide sanitization and safety filtering for AI-generated content using Google Model Armor templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 10:49 PM