Threat
Security checks across malware telemetry and agentic risk
Overview
This is a plain threat-modeling checklist skill with no code execution, data access, installation hooks, or persistence behavior.
Reasonable to install if you want a structured threat-modeling workflow. Because this skill may lead discussions about sensitive systems, avoid putting real secrets, credentials, or unnecessary confidential architecture details into shared notes.
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
65/65 vendors flagged this skill as clean.