Security audit
thinking-model-router
Security checks across malware telemetry and agentic risk
Overview
This skill is a text-only router for choosing thinking skills and does not request local access, persistence, credentials, or execution authority.
This appears safe to install as a lightweight reasoning router. It may influence which thinking skill an agent chooses, but it does not add execution capability or access sensitive 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.
Static analysis
No suspicious patterns detected.