Back to skill

Security audit

OpenClaw Browser Relay Reliability

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow browser-relay reliability guide with disclosed code areas and verification steps, and it does not include hidden execution, credential access, persistence, or external payload behavior.

Before installing, note that this skill is meant for OpenClaw browser relay maintenance and may lead an agent to edit browser extension relay and download-path code in a project. That authority is purpose-aligned and disclosed; review resulting code changes normally before merging or running them.

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
  • 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