Vulnerability in Claude Extension for Chrome Exposes AI Agent to Takeover

Because a message handler in Claude in Chrome accepts and forwards arbitrary prompts, the attacker can perform remote prompt injection and control the AI agent’s actions.While Claude enforces user confirmation for sensitive actions, as well as policies that prevent certain actions, and makes decisions based on certain inputs, LayerX discovered that the attacker’s script could bypass these protections.The company was able to forge user approval by repeatedly sending a confirmation message and relied on Document Object Model (DOM) manipulation to dynamically modify UI elements and alter Claude’s perception of the actions.It was also able to gain visibility into command execution through repeated triggering of the action and by observing the effects.“This vulnerability effectively breaks Chrome’s extension security model by allowing a zero-permission extension to inherit the capabilities of a trusted AI assistant,” LayerX says.This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

While Claude enforces user confirmation for sensitive actions, as well as policies that prevent certain actions, and makes decisions based on certain inputs, LayerX discovered that the attacker’s script could bypass these protections.The company was able to forge user approval by repeatedly sending a confirmation message and relied on Document Object Model (DOM) manipulation to dynamically modify UI elements and alter Claude’s perception of the actions.It was also able to gain visibility into command execution through repeated triggering of the action and by observing the effects.“This vulnerability effectively breaks Chrome’s extension security model by allowing a zero-permission extension to inherit the capabilities of a trusted AI assistant,” LayerX says.This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

The company was able to forge user approval by repeatedly sending a confirmation message and relied on Document Object Model (DOM) manipulation to dynamically modify UI elements and alter Claude’s perception of the actions.It was also able to gain visibility into command execution through repeated triggering of the action and by observing the effects.“This vulnerability effectively breaks Chrome’s extension security model by allowing a zero-permission extension to inherit the capabilities of a trusted AI assistant,” LayerX says.This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

It was also able to gain visibility into command execution through repeated triggering of the action and by observing the effects.“This vulnerability effectively breaks Chrome’s extension security model by allowing a zero-permission extension to inherit the capabilities of a trusted AI assistant,” LayerX says.This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

“This vulnerability effectively breaks Chrome’s extension security model by allowing a zero-permission extension to inherit the capabilities of a trusted AI assistant,” LayerX says.This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

This attack chain, the company says, allows an attacker to weaponize Claude to exfiltrate data from Gmail, GitHub, or Google Drive, as well as to send emails, delete data, and share documents on behalf of the user.When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

When notified of the issue, Anthropic told LayerX it was working on a patch, but the fix only partially addressed the underlying vulnerability, through “internal security checks to prevent extensions running in ‘standard’ mode from executing remote commands”.Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

Because the root cause of the weakness was not addressed, an attacker can simply switch the extension to ‘privileged’ mode and bypass the fix. The user is never notified or asked to approve the switch, LayerX says.Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

Related:Claude Code OAuth Tokens Can Be Stolen Through Stealthy MCP HijackingRelated:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

Related:Claude AI Guided Hackers Toward OT Assets During Water Utility IntrusionRelated:Anthropic Unveils Claude Security to Counter AI-Powered Exploit SurgeRelated:Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

Source: SecurityWeek