Security audit
IPQualityScore
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent development and ClawHub operations helpers with disclosed use of local tools, admin commands, and review subprocesses.
Install only if you trust the publisher and intend to use these skills for Convex development or ClawHub staff workflows. Review the admin and autoreview commands before running them, because they can use existing CLI credentials, send review context to external model tools, send staff email, or change moderation/account/package state when explicitly confirmed.
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.