ClawHub
Back to skill

Security audit

Fnos Openclaw Autostart

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed manual patch for OpenClaw autostart; the main risk is service disruption from editing deployed application files.

Install only if you are comfortable patching deployed OpenClaw/FnOS files manually. Take the backups first, expect a monitor restart or brief interruption, and be prepared to restore the .bak files after mistakes or application updates.

SkillSpector

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill directs users to modify deployed application files in place and later kill the running monitor process to apply changes, but it does not present a prominent upfront warning that these actions can break the app, disrupt service, or be reverted by updates. In this context, the patch also injects new backend routes and startup behavior into a privileged service, so a mistake in the edit or restart sequence could cause loss of availability or leave the application in an inconsistent state.

Static analysis

No suspicious patterns detected.