ClawHub
Back to skill

Security audit

Openclaw Cfg Safe Edit

Security checks for vulnerabilities and agentic risk

Overview

This skill only adds a documentation-check workflow before editing OpenClaw configuration files and does not show hidden, destructive, persistent, or credential-seeking behavior.

Before installing, expect this skill to make agents verify OpenClaw config options against local or online documentation before editing. Consider tightening the trigger wording if you only want it used for specific OpenClaw config paths, and note that the instructions are currently Chinese-only.

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)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The natural-language content is written exclusively in Chinese and does not indicate that the user can choose another language or that the locale restriction is intentional for a region-specific use case. This can violate language/locale policy when a skill implicitly forces one language without user opt-in.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation condition includes "任何 OpenClaw 配置文件" alongside broad file patterns, but does not clearly bound which requests should or should not invoke the skill. Without exclusions or negative examples, ordinary configuration-editing requests may trigger the skill more broadly than intended.

Static analysis

No suspicious patterns detected.