Security audit
AI Gen Guard -生成式 AI 服务合规护栏
Security checks across malware telemetry and agentic risk
Overview
This skill is a local text-based compliance checker with no evidence of hidden networking, persistence, credential access, or destructive behavior.
Reasonable to install if you want a local compliance self-check aid. Treat its output as informational only, especially because legal and regulatory requirements may change and the skill itself says it is not legal advice.
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
53/53 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.