Security audit
Dovetail
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent ClawHub/Convex workflow guidance with disclosed command use and no evidence of hidden exfiltration or destructive behavior.
Install/use this only in the ClawHub maintenance context and with trusted repo credentials. Review commands before running workflows that publish proof, touch GitHub, run Convex deploy/dev commands, invoke full-access autoreview, or perform moderation actions such as bans, unbans, role changes, or skill restoration.
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.