gws-modelarmor
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the
gwsbinary and uses it to execute shell commands for interacting with Google Model Armor APIs. It provides helpers for sanitization and template management.\n- [PROMPT_INJECTION]: The skill handles untrusted data by design as part of its filtering function, creating a surface for indirect injection attacks.\n - Ingestion points: User prompts and model responses provided to the
+sanitize-promptand+sanitize-responsesub-skills.\n - Boundary markers: The
SKILL.mddoes not specify explicit boundary markers or delimiters for the untrusted content it processes.\n - Capability inventory: The skill has the ability to execute shell commands via the
gwsCLI tool.\n - Sanitization: The primary purpose of the skill is to perform safety filtering using Google Model Armor templates.
Audit Metadata