CVE-2026-70331

Edge for iOS could mishandle input used for LLM prompts

Microsoft · Microsoft Edge (Chromium-based) / Microsoft Edge for iOS

First documented disclosure · Review checkpoint

Summary

Prompt-input handling could permit spoofing and limited data changes.

Severity and exploitation evidence

Medium · 5.4/10 · 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

Input used for LLM prompting is not properly neutralized.

Conditions required

The vendor FAQ requires visiting an attacker-controlled page and two tap gestures that activate autofill.

Potential impact

Some sensitive information can be viewed and changed; availability is not affected in the vendor assessment.

Affected versions and configurations

Microsoft Edge (Chromium-based): 1.0.0.0 to before 150.0.4078.50; Microsoft Edge for iOS: 1.0.0.0 to before 150.0.4078.50.

Fix and mitigation status

Microsoft Edge (Chromium-based)/Microsoft Edge for iOS: 150.0.4078.50.

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 2026-08-28; CNA initial publication is 2026-08-28, and current CNA datePublic is 2026-08-28T14: 00: 00.000Z. Microsoft CVSS 3.1 base score is 5.4; separate MSRC severity label: Moderate. The manufacturer marks Exploited: No in this reviewed entry. That is an attribution, not an assurance against future exploitation.

Sources