What is the CVSS score of EUVD-2026-28449?

EUVD-2026-28449 has a CVSS 3.1 base score of 7.5 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N. EPSS exploitation probability: 0.1%.

Which versions of Copilot Chat (Microsoft Edge) are affected by EUVD-2026-28449?

Microsoft Copilot Chat for Edge contains a remote command injection vulnerability (CVE-2026-33111) that allows unauthenticated attackers to extract sensitive information through network requests…. A patch is available.

How to fix or mitigate EUVD-2026-28449?

Within 24 hours: Identify all Edge browser deployments with Copilot Chat enabled across your organization using endpoint management tools. Within 7 days: Deploy the latest Microsoft Edge patch (version 133.0.3065.67 or later per MSRC advisory) via WSUS, Intune, or your configuration management platform; verify deployment completion on 95%+ of endpoints. Within 30 days: Conduct a complete audit of Edge usage in sensitive environments and consider disabling Copilot Chat feature organization-wide pending further guidance, or restricting it to approved use cases only.

Copilot Chat (Microsoft Edge) EUVD-2026-28449

| CVE-2026-33111 HIGH

Command Injection (CWE-77)

2026-05-07 microsoft

GHSA-gfjx-9vr9-m736

Microsoft Command Injection

7.5

CVSS 3.1 · NVD

Temporal: 6.5

Severity by source

NVD PRIMARY

7.5 HIGH

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

CIRCL (temporal)

6.5 MEDIUM

cvss

Primary rating from NVD.

CVSS VectorNVD

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

None

Availability

None

Lifecycle Timeline

Analysis Generated

May 07, 2026 - 22:01 vuln.today

CVE Published

May 07, 2026 - 20:58 nvd

HIGH 7.5

DescriptionCVE.org

Improper neutralization of special elements used in a command ('command injection') in Copilot Chat (Microsoft Edge) allows an unauthorized attacker to disclose information over a network.

AnalysisAI

Remote unauthenticated command injection in Microsoft's Copilot Chat for Edge browser enables information disclosure via crafted network requests. The CVSS vector (AV:N/AC:L/PR:N/UI:N) indicates attackers can exploit this remotely without authentication or user interaction, though impact is limited to confidentiality (C:H/I:N/A:N). Microsoft has released a patch per MSRC advisory. No active exploitation confirmed by CISA KEV at time of analysis, though the low attack complexity and lack of authentication requirements make this readily exploitable once technical details emerge.

Technical ContextAI

This vulnerability affects Microsoft's Copilot Chat integration within the Edge browser (CPE: cpe:2.3:a:microsoft:copilot_chat_(microsoft_edge)). The root cause is CWE-77 (Improper Neutralization of Special Elements used in a Command), indicating the application fails to properly sanitize user-controlled input before passing it to a command interpreter or system shell. In the context of a browser-integrated AI chat feature, this likely occurs when processing chat inputs, URLs, or API responses that contain special characters or command sequences. The vulnerability allows injection of malicious commands that execute in the security context of the Copilot Chat component, though scope is unchanged (S:U) meaning the vulnerable component and impacted component are the same.

RemediationAI

Apply the vendor-released patch available through Microsoft Security Response Center at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-33111. For Microsoft Edge deployments, enable automatic updates or manually update to the patched version specified in the MSRC advisory. As a temporary compensating control if patching is delayed, disable Copilot Chat functionality in Edge via Group Policy (Administrative Templates > Microsoft Edge > Enable Copilot Chat = Disabled) or edge://flags by disabling experimental AI features, though this eliminates the feature entirely. For enterprise environments, network-level controls blocking external Copilot API endpoints may reduce exposure but will also break legitimate Copilot functionality and may not prevent exploitation via cached or local command injection vectors. No workaround fully mitigates without disabling the vulnerable component.