Security audit
Dynamic Model Selector
Security checks across malware telemetry and agentic risk
Overview
This skill is a local model-recommendation helper and does not show hidden access, data collection, or unsafe actions.
This is reasonable to install if you want a simple heuristic model-selection helper. Its model availability and cost information may become outdated, and users should avoid passing highly sensitive prompts as shell arguments because normal shell history may retain them.
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.
Static analysis
No suspicious patterns detected.