ClawHub
Back to skill

Security audit

Registrychain Setup

Security checks for vulnerabilities and agentic risk

Overview

This setup skill appears aligned with installing RegistryChain, but it makes persistent agent-environment changes and broadens tool access without a clear confirmation or rollback boundary.

Install only if you trust the RegistryChain repository and are comfortable with persistent OpenClaw and Codex configuration changes. Before running it, verify the full commit or release, review package.json and dependencies, back up ~/.openclaw/openclaw.json, and ask for explicit uninstall steps for the plugin, copied skill, extension directory, and tools-profile change.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill can activate on a generic mention of RegistryChain even when the user did not explicitly request installation or environment modification. Because this skill performs cloning, package installation, plugin enablement, configuration changes, and service restart, over-broad triggering increases the chance of unintended privileged or system-modifying actions.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The setup flow performs multiple persistent system changes: cloning untrusted code from a remote repository, installing dependencies, linking and enabling a plugin, copying skill files, changing the tools profile to 'full', and restarting the gateway. Without an explicit warning and confirmation boundary, a user could trigger substantial environment changes they did not understand or intend, and expanding the tools profile increases the blast radius if the plugin or future actions are compromised.

Static analysis

No suspicious patterns detected.