What is the CVSS score of CVE-2025-53774?

CVE-2025-53774 has a CVSS 3.1 base score of 6.5 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N. EPSS exploitation probability: 0.1%.

Which versions of 365 Copilot Chat are affected by CVE-2025-53774?

CVE-2025-53774 presents notable security risk, a command injection vulnerability rated CVSS 6.5. Exploitation could allow attackers to execute code or inject malicious input.

How to fix or mitigate CVE-2025-53774?

Within 30 days: Identify affected systems and apply vendor patches as part of regular patch cycle. Validate input sanitization for user-controlled parameters.

365 Copilot Chat CVE-2025-53774

MEDIUM

Command Injection (CWE-77)

2025-08-07 secure@microsoft.com

Command Injection Microsoft Information Disclosure 365 Copilot Chat

6.5

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

6.5 MEDIUM

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

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

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

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

None

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 19:05 vuln.today

CVE Published

Aug 07, 2025 - 21:15 nvd

MEDIUM 6.5

DescriptionCVE.org

Microsoft 365 Copilot BizChat Information Disclosure Vulnerability

AnalysisAI

Microsoft 365 Copilot BizChat Information Disclosure Vulnerability. Rated medium severity (CVSS 6.5), this vulnerability is remotely exploitable, no authentication required, low attack complexity. No vendor patch available.

Technical ContextAI

This vulnerability is classified as Command Injection (CWE-77), which allows attackers to inject arbitrary commands into system command execution. Microsoft 365 Copilot BizChat Information Disclosure Vulnerability Affected products include: Microsoft 365 Copilot Chat.

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Use parameterized APIs, avoid shell execution, validate input with strict allowlists.