Skip to main content

Microsoft Copilot CVE-2026-55145

| EUVDEUVD-2026-44226 HIGH
Command Injection (CWE-77)
2026-07-14 microsoft GHSA-534g-wpcr-fm9q
7.1
CVSS 3.1 · NVD
Share

Severity by source

Vendor (microsoft) PRIMARY
MEDIUM
qualitative
NVD
7.1 HIGH
AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N
vuln.today AI
7.1 HIGH

Network-reachable service needing an authenticated low-privileged account (PR:L), no user interaction, low complexity; command injection yields high confidentiality but only limited integrity and no availability impact.

3.1 AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N
4.0 AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (microsoft).

CVSS VectorNVD

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
Low
Availability
None

Lifecycle Timeline

6
Analysis Updated
Jul 22, 2026 - 16:44 vuln.today
v2 (cvss_changed)
Re-analysis Queued
Jul 22, 2026 - 16:37 vuln.today
cvss_changed
Severity Changed
Jul 22, 2026 - 16:37 NVD
MEDIUM HIGH
CVSS changed
Jul 22, 2026 - 16:37 NVD
6.3 (MEDIUM) 7.1 (HIGH)
Analysis Generated
Jul 22, 2026 - 16:35 vuln.today
CVE Published
Jul 14, 2026 - 17:09 cve.org
MEDIUM 6.3

DescriptionNVD

Improper neutralization of special elements used in a command ('command injection') in Outlook Copilot allows an authorized attacker to perform tampering over a network.

AnalysisAI

Command injection in Outlook Copilot (Microsoft Copilot) lets an authenticated, low-privileged attacker inject unneutralized special elements over the network to tamper with the service, with Microsoft's CVSS rating a high confidentiality impact alongside limited integrity impact. The flaw was reported and fixed by Microsoft (MSRC CVE-2026-55145) and carries a CVSS 3.1 base score of 7.1. No public exploit identified at time of analysis, and CISA SSVC records exploitation status as none.

Technical ContextAI

The affected component is Microsoft Copilot as surfaced within Outlook, the AI assistant integrated into Microsoft 365. The root cause is CWE-77, improper neutralization of special elements used in a command, meaning attacker-supplied input reaches a command-processing context where special characters are not sanitized, allowing the input to alter the intended command. In an AI-assistant context this class typically arises where natural-language or structured user input is passed into downstream tooling, plugin invocations, or backend command interpreters without adequate escaping. The single CPE identified, cpe:2.3:a:microsoft:microsoft_copilot:*:*:*:*:*:*:*:*, indicates the Microsoft Copilot application/service itself rather than a specific on-premises version, consistent with a cloud-delivered service.

RemediationAI

Patch available per vendor advisory: Microsoft reports a fix is available and, as a cloud-delivered service, remediation is largely applied service-side by Microsoft - administrators should confirm their tenant reflects the fix and review the MSRC guidance at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-55145 for any customer-side action or client update required. Because exploitation requires an authenticated low-privileged account, compensating controls include tightening account governance and enforcing multi-factor authentication to reduce the pool of accounts that could abuse the flaw, and restricting or auditing Copilot access for users who do not require it (trade-off: reduced productivity for those users). Monitor Outlook/Copilot audit logs for anomalous assistant activity while the fix propagates. Do not defer solely on the low EPSS score given the high confidentiality impact.

Share

CVE-2026-55145 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy