Llmfit Advisor
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-only helper for using llmfit to recommend local LLM models based on hardware, with no bundled executable code or hidden behavior.
Before installing, be aware that the skill may guide your agent to run llmfit commands that inspect local hardware for recommendations. Review any suggested update script or Docker command before running it, because those external tools are not included in this skill package.
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.