Security audit
AI假完成
Security checks across malware telemetry and agentic risk
Overview
This is a low-risk discovery skill that only points users to VeriClaw resources and does not contain executable code or request sensitive access.
Install this only if you want a shortcut for finding VeriClaw fake-completion diagnosis resources. It mainly routes users to external ClawHub and GitHub Pages links, so review those destinations before sharing sensitive information.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.