Count
Security checks across malware telemetry and agentic risk
Overview
This is a simple reference skill that prints static documentation and does not show evidence of accessing data, credentials, the network, or system state.
This appears low risk to install as a static reference helper. It is still a third-party skill, so treat its generic operational advice as documentation rather than verified guidance for your own systems.
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.