深度认知能力构建系统
Security checks across malware telemetry and agentic risk
Overview
This is a Chinese-language cognition and logic training guide with no code, install actions, credential use, persistence, or hidden system access.
Safe to install as a reference-style skill. Expect Chinese-language guidance and treat tool or platform recommendations as optional; separately confirm before connecting external services or sharing private notes with any AI or knowledge-management tool.
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.