Back to skill

Security audit

Registrychain Setup

Security checks for vulnerabilities and agentic risk

Overview

This setup skill is purpose-aligned, but it persistently installs third-party plugin code and expands OpenClaw to a global full tool profile without enough scoping or rollback guidance.

Review this skill before installing. It is not evidence of malware, but it will download and enable third-party code, copy a skill into your Codex skills directory, change OpenClaw's global tool profile to full, and force-restart the gateway. Prefer a reviewed full commit hash, a lockfile-based install, explicit backup and rollback steps, and a narrower tool profile if OpenClaw supports one.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:20
Finding

Unreviewed Third-Party Plugin and Dependency Installation

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:41
Finding

Global Unrestricted Tool-Profile Escalation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs the agent to clone code from a remote repository, install dependencies, register a plugin, copy files into the user's environment, and change configuration without any explicit warning or confirmation step about persistent local changes. Even though the repo is pinned to a commit and npm scripts are disabled, these actions still materially alter the system and expand trust to third-party code, which can surprise users and increase exposure if performed automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction to run openclaw gateway --force performs a forced restart of a service but does not warn the user about interruption, possible termination of active sessions, or other availability effects. In an agent skill, omitting that warning is dangerous because the step may be executed mechanically, causing avoidable disruption to the local environment.

Content

No source excerpt is available for this finding.