Find Management Consultant
Security checks across malware telemetry and agentic risk
Overview
The artifacts appear to be disclosed ClawHub maintainer/developer workflow instructions, with no evidence of hidden exfiltration, deception, or destructive behavior.
Use this in a ClawHub development or maintainer context. Before running autoreview, understand that it can launch nested Codex review with full local access by default; use the documented opt-out if that authority is not acceptable.
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
64/64 vendors flagged this skill as clean.
