ClawHub
Back to skill

Security audit

Config Safe

Security checks for vulnerabilities and agentic risk

Overview

This skill is a cautious guide for modifying OpenClaw configuration and requires preview, validation, and explicit user confirmation before writes.

Installers should understand that this skill can change OpenClaw Gateway configuration and cause a Gateway restart after confirmation. Use it only when you intend to modify OpenClaw settings, review the preview carefully, and avoid confirming changes that alter channels, tokens, agents, or sandbox behavior unless you understand the effect.

A.I.G

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

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
96% confidence
Finding
The trigger list includes highly generic activators such as “config” and broad phrases like “修改配置/更改配置”, which can match ordinary discussion rather than an explicit request to invoke this high-risk skill. In context, this skill can lead to configuration writes and gateway restarts after confirmation, so accidental invocation increases the chance of unintended sensitive operations or confusing the user into an unsafe config flow.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The natural-language instructions and warnings in this skill are all presented in a single language, which can impose a locale preference on users without opt-in. Under the language/locale policy criterion, this is a policy concern unless the file offers an alternative language or explains that the skill is intentionally region-specific.

Static analysis

No suspicious patterns detected.