CVE-2026-50519

Copilot Chat insecure defaults could expose information

Microsoft · GitHub Copilot Chat

First documented disclosure · Review checkpoint

Summary

An insecure initial resource setting could permit information disclosure.

Severity and exploitation evidence

Medium · 6.5/10 · CVSS 3.1. Severity source.

Exploitation not established: Microsoft marks Exploited: No. The reviewed material does not establish malicious exploitation against users.

Exploitation evidence source

Technical severity is not a measure of observed attacks or of risk to your deployment. Attempts, demonstrations, and successful compromise retain the qualifications in the source.

How the weakness works

A resource starts with an insecure default.

Conditions required

A user interacts with attacker-influenced content over a network; the vendor does not specify the exact workflow.

Potential impact

Disclosure of confidential information; the public description does not identify the data.

Affected versions and configurations

GitHub Copilot Chat: 1.0.0 to before 1.123.2.

Fix and mitigation status

GitHub Copilot Chat: 1.123.2.

Practical next steps

Install the vendor-listed corrected build for the applicable product and platform.

Operating lesson

Enforce the affected trust boundary independently of AI-generated content, caller identity and user-interface safeguards.

Evidence and limits

Historical backfill from a November 19–20 CVE update batch. Earliest reviewed public date is 2026-06-09; CNA initial publication is 2026-06-19, and current CNA datePublic is 2026-06-09T14: 00: 00.000Z. Microsoft CVSS 3.1 base score is 6.5; separate MSRC severity label: Important. The manufacturer marks Exploited: No in this reviewed entry. That is an attribution, not an assurance against future exploitation.

Sources