Ollama

Security checks across malware telemetry and agentic risk

Overview

This Ollama skill is a straightforward user-run helper that sends prompts to a configured Ollama API endpoint, with the main caution being its disclosed non-local default host.

Before installing or running it, confirm that http://100.66.1.2:11434 is your intended Ollama server. If not, set OLLAMA_HOST to a trusted local or controlled endpoint, and avoid sending sensitive prompts to remote or unauthenticated Ollama hosts.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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

Findings (1)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documentation indicates capabilities that involve environment variables and network access, and even references host configuration and API interaction, but it does not declare permissions. This creates a transparency and policy-enforcement gap: users or orchestration systems may approve or run the skill without understanding that it can access external services and local configuration, increasing the risk of unintended data exposure or unauthorized network use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal