ClawHub
Back to skill

Security audit

Wanx

Security checks for vulnerabilities and agentic risk

Overview

This Wanx skill mostly matches its stated purpose, but its setup path can run an unverified remote installer script if the CLI is missing.

Before installing, review the oo CLI installer path yourself, prefer an official signed or checksum-verifiable installation method, and only allow setup or account connection steps when you intentionally want this skill to use your OOMOL-connected Wanx account and any associated credits.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
98% confidence
Finding
The skill instructs the agent to install software by piping a remote script directly into bash, which is a classic arbitrary code execution pattern. If the remote server, transport, or installation script is compromised, the agent could execute attacker-controlled code on the host with the current user's privileges.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger scope is overly broad because it instructs the agent to use this skill for ANY Wanx request, including reading, creating, and updating data, instead of narrower action-specific invocation. This increases the chance the skill is selected in situations involving state-changing operations, expanding exposure to unsafe command paths and making accidental misuse more likely.

Static analysis

No suspicious patterns detected.