AI Model Watcher
Security checks across malware telemetry and agentic risk
Overview
The available scan inputs do not show malicious or review-worthy behavior, but the artifact contents were not present for full local confirmation.
Install only if the package page and publisher match what you expect. Because the local artifact contents were not available in this adjudication workspace, review the visible skill files before use, especially for commands that install software, read private files, use credentials, or persist data.
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.