Review Tui
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is coherent and disclosed, with high-impact maintainer and Convex workflows that are scoped to their stated purposes.
Install only if you expect an agent to help with ClawHub/Convex maintenance. Be aware that some workflows can use authenticated GitHub or ClawHub staff privileges, run review tools with broad local access, publish UI proof artifacts, or change production-facing Convex/moderation state; review commands before writes and keep credentials scoped.
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
65/65 vendors flagged this skill as clean.