Skip to content
WatchlistHigh

CVE-2025-32711365 Copilot Vulnerability

Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.

Published Jun 12, 2025 · Updated Feb 26, 2026 · Also known as TR-25-0126

Key Facts

Patch in the next maintenance window
  • CVE-2025-32711 is a high-severity vulnerability (CVSS 7.5 v3.1) affecting 365 Copilot (Microsoft).
  • It is not listed in any known-exploited vulnerabilities catalog. No public exploit code is known.
  • EPSS estimates a 8.0% probability of exploitation in the next 30 days.
  • No fixed version is listed yet; check the vendor advisory for mitigations.
  • Brandefense priority: patch in the next maintenance window, because of its high severity, although no exploitation is known.

Scores

CVSS v3.1

7.5

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

EPSS (30-day exploit likelihood)

8.0%

Higher than 94.7% of all scored CVEs

Exploit maturity

Proof of concept

ATLAS score

49/100

Publication score, see How it works

Exploitation Verdict

KEV listed

Not listed

Federal due date

None

No federal due date

Ransomware use

Not reported

Attributed actors

None named

Exploit & Defence Guidance

Exploit maturity

Proof of concept

Public exploit code

5

Proof-of-concept links

In-the-wild evidence

0

Reports of active use

Description

Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.

Affected Products

2 affected entries in total
ProductAffected versionsFixed in
365 CopilotMicrosoftSee advisoryn/a

Timeline

  1. Publicly disclosed

    Jun 12, 2025

  2. Last updated

    Feb 26, 2026

Weakness Type

  • CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')

FAQ

Common Questions.

Is CVE-2025-32711 On Your Attack Surface?

Brandefense matches it against the products discovered on your perimeter and opens a finding the day a CVE like this is listed.

Request A Demo

Figures as of Oct 19, 2026. Compiled by Brandefense technologies from public vulnerability catalogs; scoring as described in How it works.

To report an error, contact Brandefense.