Gws Modelarmor Sanitize Response
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow Google Model Armor helper that documents how to send model responses through a configured sanitization template.
Install only if you trust the `gws` CLI and your generated shared `gws` instructions. Use least-privilege Google credentials, verify the target Model Armor template, and avoid sending content that should not be processed by your configured Google service.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.