Auto
Security checks across malware telemetry and agentic risk
Overview
The available evidence shows a coherent skill with no scanner findings or artifact-backed signs of hidden, destructive, or overbroad behavior.
This appears safe to install based on the available review signals. As with any skill, users should still read the skill text and confirm it only asks the agent to do what they expect before using it with sensitive content.
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.