Gws Keep
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts appear coherent and user-directed, with no evidence of hidden execution, exfiltration, destructive behavior, or misleading purpose.
Install only if you intend to let the agent help with ClawHub/Convex maintenance workflows. Review commands before running actions that publish proof, contact GitHub/Convex/ClawHub services, or change moderation state, and make sure the active credentials belong to the account and environment you intend to use.
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.