ClawHub
Back to skill

Security audit

Open WebUI

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Open WebUI API helper that sends user-chosen prompts, files, and model-management requests to the configured Open WebUI instance.

Install this only if you want the agent to use your Open WebUI API token. Prefer a local or trusted HTTPS Open WebUI instance, review any request before uploading private files or using remote RAG, and confirm model deletion or large model pulls carefully.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly instructs the agent to use environment variables for authentication and to make outbound network requests to arbitrary Open WebUI instances, yet no explicit permission declaration is present. This creates a governance gap: an agent may access secrets and external services without transparent capability scoping or user-reviewable permission metadata.

Context Leakage

High
Category
Data Exfiltration
Content
**Activate this skill when the user wants to:**
- List available models from their Open WebUI instance
- Send chat completions to models through Open WebUI
- Upload files for RAG (Retrieval Augmented Generation)
- Manage knowledge collections and add files to them
- Use Ollama proxy endpoints (generate, embed, pull models)
Confidence
82% confidence
Finding
Send chat

Tool Parameter Abuse

High
Category
Tool Misuse
Content
### Confirmation Required

Always confirm before:
- **Deleting models** (`DELETE /ollama/api/delete`) - Irreversible
- **Pulling large models** - May take significant time/bandwidth
- **Deleting knowledge collections** - Data loss risk
- **Uploading sensitive files** - Privacy consideration
Confidence
88% confidence
Finding
DELETE /ollama/api/delete`)

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.