WeChat Intro
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill materials are coherent and purpose-aligned, with no artifact-backed evidence of hidden exfiltration, destructive behavior, or deceptive instructions.
Reasonable to install for trusted ClawHub or Convex maintainers. Before use, make sure operators understand that some workflows can run broad local review commands, publish UI proof, or perform moderation actions, and should be invoked only with clear targets and appropriate credentials.
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.