Happyfox Chat

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: happyfox-chat Version: 1.0.4 The skill bundle provides instructions for an AI agent to integrate with HappyFox Chat via the Membrane CLI. It outlines standard procedures for authentication, connection management, and executing API actions (e.g., retrieving chat transcripts or agent profiles) through the Membrane platform. The instructions in SKILL.md and metadata in _meta.json do not contain any evidence of malicious intent, data exfiltration, or suspicious obfuscation.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the agent runs a create, update, delete, ban, integration, or billing-related action, it could change HappyFox Chat account data.

Why it was flagged

The skill uses a generic action runner for the HappyFox Chat connection. This is appropriate for an integration, but broad action execution can include account-changing operations if the selected action is mutating.

Skill content
Use action names and parameters as needed. ... membrane action run <actionId> --connectionId=CONNECTION_ID --input '{"key": "value"}' --json
Recommendation

Confirm the exact action and input before running state-changing operations, and prefer read-only actions unless the user clearly requested a change.

What this means

The connected Membrane/HappyFox account may allow the agent to read or modify support data depending on granted permissions.

Why it was flagged

The skill requires delegated authentication through Membrane to access HappyFox Chat. This is expected for the integration, but it means account credentials or tokens are part of the workflow.

Skill content
Requires network access and a valid Membrane account ... Membrane handles authentication and credentials refresh automatically
Recommendation

Use a dedicated or least-privileged HappyFox/Membrane account when possible, and disconnect the integration when it is no longer needed.

What this means

The behavior of the integration depends on the currently published Membrane CLI package at install time.

Why it was flagged

The setup relies on a globally installed npm package pinned to the latest version. This is a normal user-directed setup step, but the exact code version is not fixed by the skill artifact.

Skill content
npm install -g @membranehq/cli@latest
Recommendation

Install the CLI from the official package source, consider pinning a known-good version, and review npm package provenance in sensitive environments.

What this means

Customer chat transcripts and visitor details could enter the agent context or be shown in outputs.

Why it was flagged

The documented actions can retrieve visitor records and chat transcripts, which may contain customer or business-sensitive information and are accessed through the Membrane integration path.

Skill content
List Visitors - Retrieve all visitors who have interacted with the chat widget ... Get Transcript - Retrieve a specific chat transcript by its ID
Recommendation

Avoid broad transcript or visitor exports unless needed, and redact sensitive customer information before sharing outputs.