OpenClaw GitHub Copilot
Security checks across malware telemetry and agentic risk
Overview
The reviewed artifacts appear to be disclosed ClawHub development and moderation workflow guidance, with no evidence of hidden exfiltration, destructive behavior, or purpose-mismatched execution.
Install or use this only in a ClawHub development/maintainer context. Review commands before running moderation, deploy, migration, or full-access review workflows, and use least-privilege tokens and non-production deployments unless you intentionally need production authority.
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.