Security audit
LLM Supervisor
Security checks across malware telemetry and agentic risk
Overview
This skill coherently switches agents between cloud and local LLMs for rate-limit fallback and shows no evidence of hidden data access, exfiltration, or destructive behavior.
Install this if you want automatic fallback from cloud LLMs to local Ollama during rate limits. Before enabling it, be comfortable with a skill that can change agent LLM profiles, defaults cloud mode to Anthropic, persists the current mode across new agents, and treats any user message containing CONFIRM LOCAL CODE as approval for local-model code tasks.
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.