ClawHub
Back to skill

Security audit

Release Package

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a real workspace browser, but it can expose workspace files too broadly over the network and to an external AI service.

Review before installing. Run only in a trusted environment, bind it to localhost, add authentication or a local-only token, restrict CORS, fix path containment with resolved-path checks, and use the AI explanation feature only for files you are willing to send to DeepSeek. Clear or disable the SQLite explanation database for sensitive projects.

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
94% confidence
Finding
The skill documentation states that AI-generated code explanations are automatically saved to SQLite, but it does not clearly warn users that generated or user-entered explanatory content will be persisted locally. In a workspace-browsing tool, those explanations may include sensitive code context, secrets, or proprietary details, so silent persistence creates a meaningful privacy and data-retention risk.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
This code sends full file contents to an external AI service, which can disclose source code, secrets, credentials, proprietary logic, or personal data outside the local environment. In a workspace browser context, users may reasonably expect local inspection, so undisclosed transmission materially increases confidentiality risk.

Static analysis

No suspicious patterns detected.