Back to skill

Security audit

Chrome Session Attach

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent guide for attaching OpenClaw to a user-selected Chrome tab, but users should treat the browser session and gateway token as sensitive.

Install only if you intend to let OpenClaw control a Chrome tab you choose. Avoid attaching banking, admin, email, or other highly sensitive sessions unless you are comfortable with the agent viewing and acting on that page, and do not paste the gateway token into chats, logs, screenshots, or shared terminals.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This skill enables an agent to attach to and control an already-authenticated Chrome tab, which can change page state, submit forms, and act with the user's existing session. The documentation presents this capability as operationally convenient but does not warn users that using it may expose accounts, modify data, or trigger irreversible actions in live services.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions tell users to print the gateway authentication token from a local config file and manually enter it into the extension, but provide no guidance on treating that token as a secret. Exposing or mishandling the token could allow unauthorized local control of the browser gateway, especially since the gateway can drive attached tabs and access sensitive authenticated browser context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions throughout the file are presented in Chinese, while some UI labels remain in English, and there is no indication that the user can choose another language. This can violate a language/locale policy when a specific language is imposed without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.