郡城AI导师
Security checks across malware telemetry and agentic risk
Overview
This is a simple AI tutoring skill with no evidence of hidden commands, data access, persistence, or unsafe behavior.
This appears appropriate to install for AI learning and coding help. As with any tutor skill, avoid sharing secrets, credentials, or proprietary code unless you intend to expose that content to the assistant, and review generated technical advice before using it in production.
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.