ClawHub
Back to skill

Security audit

Intiface Direct

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it claims, but it controls intimate hardware with indefinite and remote-control modes that are not documented with enough safety and access-control guidance.

Review this carefully before installing. Use localhost by default, avoid LAN exposure unless the network and participants are trusted, and make sure you understand how to stop the device before using loop or pattern modes. Prefer timed commands and verify the device has actually stopped after interruptions or disconnects.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (5)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly advertises continuous device control with 'no timeout' and only notes that it resends every 3 seconds, without any nearby safety warning that the device will continue operating until manually stopped. In the context of intimate-device control, omission of stop/failsafe guidance can contribute to physical safety risks, unintended prolonged stimulation, and loss of user control if the terminal, script, or connection state is misunderstood.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README advises using a LAN IP for remote control but provides no warning about exposing the WebSocket service to other users or systems on the network. In this skill's context, remote access to intimate-device controls raises meaningful privacy, consent, and unauthorized-access concerns, especially if users assume localhost-style trust boundaries still apply.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Skill Enumeration

Medium
Category
Agent Snooping
Content
Control any [Buttplug.io-compatible device](https://iostindex.com) — 700+ toys across all major brands — from natural language through OpenClaw. Connects directly to **Intiface Central** via WebSocket using the **Buttplug v4 protocol**. No MCP bridges, no unstable middleware.

The full agent-friendly SKILL.md is in `skills/intiface-direct/SKILL.md`. It includes:

- **🤖 Zero-to-Hero Guide** for any agent learning from scratch
- **🔧 Setup & Prerequisites** — Intiface Central, device pairing, dependencies
Confidence
80% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Unpinned Dependencies

Low
Category
Supply Chain
Content
{
  "dependencies": {
    "ws": "^8.21.1"
  }
}
Confidence
40% confidence
Finding
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Static analysis

No suspicious patterns detected.