Terminology
Security checks across malware telemetry and agentic risk
Overview
This is a simple UML terminology reference skill with no executable behavior or hidden access requests.
This skill appears safe to install as a terminology reference. Be aware it tells the agent not to edit the skill's own files and to use the normal OpenClaw update command instead, but it does not request sensitive access or perform actions on its own.
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
59/59 vendors flagged this skill as clean.