ClawHub
Back to skill

Security audit

OpenClaw Safe Config

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OpenClaw configuration-editing checklist, not hidden automation or data access.

Install only if you want an agent to help edit OpenClaw gateway settings. Review each proposed config change before restart, because settings like sessions, tools, agents, and models can affect future agent behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 103)May include surrounding context.

md
A single unknown key in `openclaw.json` makes the gateway refuse to start. There's no warning — it just fails. The backup + source verification + doctor flow takes 30 seconds and prevents complete system outages.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 34)May include surrounding context.

If the key doesn't appear in source → it doesn't exist, don't add it.

3. Edit the config

Use Python to safely read/modify/write (avoids JSON syntax errors):

bash
cat ~/.openclaw/openclaw.json | python3 -c "
import json, sys

Static analysis

No suspicious patterns detected.