ClawHub
Back to skill

Security audit

SMB Client Onboarding

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its onboarding-tracker purpose, but it sends client contact email data to an external LLM despite only disclosing client name and stuck-step context.

Review this before installing if client contact details or contract values are sensitive. Use it only on a machine where local JSON records are acceptable, and avoid setting MINIMAX_API_KEY or using reminder generation unless you are comfortable sending client identifiers, including contact email, to MiniMax.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The reminder flow sends client-identifying and operational data, including client name, contact email, and onboarding status, to a third-party LLM service without explicit user notice or consent in the command flow. In this skill context, that is more dangerous because the tool handles customer onboarding data that may be commercially sensitive or subject to privacy expectations.

External Transmission

Medium
Category
Data Exfiltration
Content
api_key, _ = get_llm_api_key()
    if not api_key:
        return None
    base_url = "https://api.minimax.chat/v1"  # pinned, no env override
    try:
        data = json.dumps({
            "model": "minimax/MiniMax-M3",
Confidence
90% confidence
Finding
This code performs an external network transmission to a third-party LLM endpoint. While the endpoint is pinned and not attacker-controlled, the transmitted prompt can contain customer contact details and onboarding information, creating a real confidentiality and data-governance risk in an onboarding tool.

Session Persistence

Medium
Category
Rogue Agent
Content
author: "NASSER AL-SOLAITTI"
description: "Local client onboarding tracker. Store client records, track onboarding steps, and generate reminder text via LLM. Use when user says 'track a new client', 'add client onboarding', 'show onboarding status', or 'onboarding checklist'.
permissions:
  - filesystem-write: write onboarding and config data to ~/.openclaw/smb-client-onboarding/
  - env: read MINIMAX_API_KEY from environment (for optional LLM reminder generation)
  - network: send client name and onboarding step context to minimax LLM API when reminder generation is used
privacy: |
Confidence
83% confidence
Finding
The skill explicitly persists client onboarding data, including names, contact emails, contract details, and status, to a local file under the user's home directory. Storing business-sensitive and potentially personal data on disk creates confidentiality and retention risks if file permissions are too broad, the host is shared, backups are exposed, or data is retained longer than expected.

Static analysis

No suspicious patterns detected.