Security audit
Model Provider Support
Security checks across malware telemetry and agentic risk
Overview
The inspected ClawHub skill artifacts are coherent maintenance/admin guidance with disclosed high-impact actions and explicit user-confirmation safeguards.
Install only in a ClawHub maintenance context. Some skills can guide admin moderation, email sending, production migrations, and GitHub PR actions, so use them with the documented dry-run, explicit target, reason, confirmation, and verification steps.
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.
Static analysis
No suspicious patterns detected.