ClawHub
Back to skill

Security audit

CLI-Hub Tools

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style skill for a broad CLI installer, but it encourages installing and running many powerful third-party tools without clear safety boundaries.

Install only if you trust the CLI-Hub package and its downstream registry. Prefer a virtual environment or container, inspect each tool before installing or launching it, and require explicit approval before browser, cloud, API, screen-recording, process-management, install, update, or uninstall actions.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill prominently instructs users to install, update, uninstall, and launch third-party CLIs, which are all system-changing actions, but provides no warning that these commands may modify the host environment, fetch untrusted packages, or execute downloaded code. In an agent-skill context, presenting such commands as routine operations increases the chance of unsafe execution without user awareness or confirmation.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises browser automation, cloud-service tooling, AI/API tools, and workflow automation utilities without any privacy or security warning about handling credentials, browser session data, cloud resources, or external network access. In practice, these categories can expose sensitive data, trigger paid cloud actions, or automate high-impact operations, so omission of warnings materially increases misuse risk.

Static analysis

No suspicious patterns detected.