ClawHub
Back to skill

Security audit

Ollama Web Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Ollama web-search wrapper that clearly discloses its API key use and outbound request behavior.

Install this only if you are comfortable providing an Ollama API key and sending search queries to Ollama. Avoid using it for confidential queries unless your Ollama account and data handling expectations permit that use.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill invokes a Node.js script that uses both network access and an environment secret (`OLLAMA_API_KEY`), but the manifest does not declare an explicit tool scope such as `permissions` or `allowed-tools`. This creates an authorization gap where agents or users may not have clear visibility or enforcement over the skill's capability to access secrets and make outbound requests, increasing the risk of unintended secret use or data exfiltration.

External Transmission

Medium
Category
Data Exfiltration
Content
max_results: Math.max(1, Math.min(n, 10)),
};

const resp = await fetch("https://ollama.com/api/web_search", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.