OpenClaw Skill Governance (Balanced Dynamic Core Pool)
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only governance skill that manages local skill status and routing without included executable code or evidence of hidden network, credential, or destructive behavior.
Safe to install as a local governance policy, but review any referenced scripts before running them because they are not part of this artifact. Keep skill-registry.json backed up or version controlled, and manually review important quarantine, retirement, or routing changes because they can affect which skills are selected automatically.
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.