Ollama Herd
Security checks across malware telemetry and agentic risk
Overview
This is a coherent instruction-only skill for managing a local Ollama fleet, with disclosed local services, model-management actions, and guardrails for disruptive changes.
Before installing, verify the PyPI package and linked repository, run router and node agents only on devices and networks you trust, and require explicit approval before model pulls, deletes, settings changes, restarts, or stops because those actions can consume significant disk space or alter local fleet behavior.
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
63/63 vendors flagged this skill as clean.