Gws Modelarmor
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent Google Model Armor helper that documents use of the gws CLI and shows no hidden execution, persistence, or destructive behavior.
Install only if you trust the gws CLI and the generated shared gws skills it depends on. Use least-privileged Google credentials, avoid sending secrets or regulated data unless your policy allows Google Model Armor processing, and confirm before creating or changing templates.
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
63/63 vendors flagged this skill as clean.