Security audit
AI助手百科全书
Security checks across malware telemetry and agentic risk
Overview
The visible skill artifacts are coherent workflow guidance with disclosed command use and approval gates, and the clean scanner signals do not show artifact-backed malicious behavior.
Before installing, confirm you trust the publisher and understand that some skills are meant for powerful staff or production workflows. Use them only with the required confirmations, and treat external review engines as third-party processors for code or diff content.
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.