Detector AI
Security checks across malware telemetry and agentic risk
Overview
This skill is a local AI-text detector whose files and behavior match its stated purpose.
Installers should understand this is a heuristic detector, not proof of authorship. Only provide text or files you intentionally want analyzed, since the script can read a user-supplied file path, but no evidence shows external upload or hidden data access.
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
67/67 vendors flagged this skill as clean.