Security audit
Feynman Technique
Security checks across malware telemetry and agentic risk
Overview
This is a static teaching-method skill that guides users through plain-language understanding checks and does not request unsafe access or execute code.
Reasonable to install if you want a structured coaching skill for testing understanding. The main caution is privacy: if you add real observed failure patterns or examples, keep sensitive personal, business, or proprietary details out unless you deliberately sanitize them.
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.