Security audit
Huo15 Edit
Security checks across malware telemetry and agentic risk
Overview
The skill materials appear to be legitimate ClawHub maintenance and review guidance with disclosed safeguards for sensitive actions.
Install only if you are comfortable giving your agent ClawHub maintainer-style guidance. Authorized staff should use the confirmation and dry-run steps exactly as written, especially for bans, restores, ownership changes, email sending, production migrations, and code review bundles that may be sent to external model tools.
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.