Security audit
critical-thinking-framework
Security checks across malware telemetry and agentic risk
Overview
This skill is a reasoning-only critical-thinking framework and does not request code execution, private data access, persistence, or account authority.
This is appropriate to install as a general reasoning aid. Users should treat its output as structured analysis rather than authoritative fact-checking, especially for medical, legal, financial, safety-critical, or regulated decisions.
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.