S³ Threat Modeling
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only threat modeling skill with no code, install actions, credentials, persistence, or hidden system access.
This skill appears safe to install as a security-review assistant. Use it only with systems you are authorized to review, and avoid pasting sensitive architecture details unless your workspace is appropriately access-controlled.
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
63/63 vendors flagged this skill as clean.