Security audit
AI方向评估笔记
Security checks across malware telemetry and agentic risk
Overview
This skill appears to be a published AI research/opinion note, not a tool that runs commands or accesses user data.
This looks safe to install as a readable discussion note. Treat its technical claims as author opinion/research commentary, but it does not appear to add tools, run code, persist processes, or access private data.
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
51/51 vendors flagged this skill as clean.