Security audit
thinking-systems
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed reasoning checklist for systems mapping and does not request unusual access or perform actions on its own.
This appears safe to install as a thinking aid. Users should expect it to shape the agent's analytical structure for systems problems, not to run tools or access data by itself.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.