Security audit
Email Cold Zh
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent maintainer tooling, but it deserves review because one helper defaults to launching a nested review agent with full sandbox bypass while other workflows can perform high-impact staff or production actions.
Install only if you want an agent to help with privileged ClawHub/Convex maintainer workflows. Use `--no-yolo` or `AUTOREVIEW_YOLO=0` for sensitive code reviews, confirm exact moderation targets and reasons before writes, and be careful with production Convex deploys, migrations, and GitHub publishing commands.
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.