Gws Modelarmor Sanitize Prompt
Security checks across malware telemetry and agentic risk
Overview
This skill is a narrow Google Model Armor command helper that documents prompt sanitization and does not include executable code.
Install this only if you trust the local `gws` CLI and your Google Cloud configuration. Avoid submitting secrets or regulated data unless the selected Model Armor template and Google Cloud data-handling terms are appropriate for that content.
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.