Security audit
GitHub Triage
Security checks across malware telemetry and agentic risk
Overview
This appears to be a legitimate ClawHub development and maintenance skill bundle, with powerful actions disclosed and tied to user-directed workflows.
Install only if you expect ClawHub maintainer/developer workflows. Some skills can run broad local reviews, interact with GitHub/Convex, publish proof artifacts, or perform authenticated moderation actions, so review the commands before approving them and use them from the intended ClawHub repo context.
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.
Static analysis
No suspicious patterns detected.
