Split
Security checks across malware telemetry and agentic risk
Overview
No artifact-backed evidence shows hidden, destructive, or deceptive behavior, and the available scanner signals do not validate a material concern.
This looks acceptable to install based on the available evidence. Because the scan noted unicode-control characters, review the rendered skill text if possible and make sure it does not contain surprising hidden instructions before granting sensitive credentials or broad filesystem 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
62/62 vendors flagged this skill as clean.