Mental Models
Security checks across malware telemetry and agentic risk
Overview
This is a simple instruction-only thinking framework with no tool use, file access, network access, credentials, or persistence.
This skill appears safe to install as a reasoning aid. Its main effect is that, when invoked, it will steer the agent toward longer structured analysis using several mental-model categories.
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
66/66 vendors flagged this skill as clean.