Security audit
famous
Security checks across malware telemetry and agentic risk
Overview
This is a self-contained Chinese thought-experiment skill about human-AI collaboration, with no executable code or hidden access requests.
This appears safe to install as a content skill. Review the Chinese thought-experiment material for quality, licensing, and fit with your use case, and avoid entering sensitive personal or business details when discussing hypothetical AI-collaboration scenarios.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.