Spoofing via unneutralized LLM prompt input
Published Aug 28, 2026 · Updated Aug 29, 2026
Prompt injection in Microsoft Edge for iOS before 150.0.4078.50 allows remote attackers to spoof browser content over a network. The browser's LLM prompting path processes attacker-controlled input without neutralizing prompt-control content, allowing generated output to misrepresent trusted information. Successful exploitation requires user interaction and can mislead the user or expose limited information, but no service interruption is reported.
Summary
What happened
Prompt injection in Microsoft Edge for iOS before 150.0.4078.50 allows remote attackers to spoof browser content over a network. The browser's LLM prompting path processes attacker-controlled input without neutralizing prompt-control content, allowing generated output to misrepresent trusted information. Successful exploitation requires user interaction and can mislead the user or expose limited information, but no service interruption is reported.
The record
- CVE
- CVE-2026-70331
- Published
- Aug 28, 2026
- Updated
- Aug 29, 2026
- Vendor
- Microsoft
- Product
- Microsoft Edge (Chromium-based)
- Classifications
- CWE-1427
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 28, 2026CVE publishedPublication date reported by the CVE source.
- Aug 29, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=1.0.0.0 <150.0.4078.50
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo