ClawHub
Back to skill

Security audit

openclaw-clawhome

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Clawhome integration skill whose sensitive steps are expected for the stated chat-connector purpose, but users should handle secrets and file uploads carefully.

Install only if you trust the external openclaw-clawhome plugin source. Treat channelSecret like a password, avoid pasting real secrets into shared terminals or logs, and rotate it if exposed. Upload only files you are comfortable sending to Clawhome, since the documented upload flow does not describe authentication, retention, deletion, or who can access the resulting URL.

SkillSpector

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

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The instructions tell users to set a channel secret directly via CLI examples but provide no warning that this value is sensitive, should not be logged, and should be stored/handled securely. This can lead to accidental exposure through shell history, screenshots, shared terminals, or copied docs, enabling unauthorized access to the channel integration.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents uploading files to an unauthenticated public endpoint and then distributing the resulting URL, but it gives no warning about privacy, data exposure, or abuse risks. In a chat integration that may handle user-provided content, this increases the chance that sensitive files are uploaded to a publicly accessible location without user awareness or access controls.

Static analysis

No suspicious patterns detected.