Security audit
Write A Skill
Security checks across malware telemetry and agentic risk
Overview
The available evidence does not show hidden, destructive, or unrelated behavior, and the supplied security scanners are clean.
Install only if you expect ClawHub maintenance workflows. Some available skills can guide admin, moderation, email, migration, or review actions, so use them from a trusted checkout with the appropriate account permissions and review any write command before approving it.
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
52/52 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.