Security audit
MxToolbox
Security checks across malware telemetry and agentic risk
Overview
The skill appears coherent and purpose-aligned, with clean scanner telemetry and no artifact-backed signs of hidden or malicious behavior.
Install or use this only in the intended ClawHub/Convex development or moderation context. Review exact commands before allowing moderation, GitHub, or full-access review actions, especially when they can change accounts, roles, public content, or repository state.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.