Security audit
Harness Control Layer
Security checks across malware telemetry and agentic risk
Overview
This is a text-only routing and safety-check skill that is coherent with its stated OpenClaw control-layer purpose.
Reasonable to install if you want a procedural control layer for routing OpenClaw work. Users should still review any incident-recording or playbook-promotion workflow before allowing it to write durable notes or change skills, because those actions can affect future agent behavior.
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
56/56 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.