Back to skill

Security audit

Assistant Configurator

Security checks for vulnerabilities and agentic risk

Overview

This documentation-only skill gives OpenClaw configuration guidance; its examples can change live settings or store credentials, but that behavior matches its stated purpose and is disclosed.

Install only if you want an assistant to help manage OpenClaw settings. Review every config.patch, restart, token, and API-key command before use, keep backups, and prefer environment variables or a secrets manager for real credentials.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill description and all user-facing guidance are written exclusively in Chinese, and one model recommendation explicitly states Chinese optimization as a preferred factor. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill includes direct examples for config.patch and restart that can change system behavior and availability, but it does not place an explicit warning immediately around those actions about service disruption, misconfiguration, or the need for user confirmation. In a configuration-management skill, users may copy these commands verbatim, increasing the chance of accidental outage or unsafe changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The examples show how to set secrets such as botToken and BRAVE_API_KEY without an explicit warning on secure secret handling, storage, rotation, and avoiding hardcoding or logging sensitive values. This can lead users to expose credentials in config files, shell history, chat logs, or version control.

Content

No source excerpt is available for this finding.