CVE-2025-59252
Published: 09 October 2025
Summary
CVE-2025-59252 is a critical-severity Command Injection (CWE-77) vulnerability in Microsoft 365 Word Copilot. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 30.8th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the Privacy and Disclosure risk domain.
The strongest mitigations our analysis identified are NIST 800-53 SC-2 (Separation of System and User Functionality) and SI-10 (Information Input Validation).
Deeper analysis
CVE-2025-59252 is an improper neutralization of special elements used in a command, classified as command injection (CWE-77), affecting Copilot. This vulnerability enables an unauthorized attacker to disclose information over a network. It has a CVSS v3.1 base score of 9.3 (AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N), indicating critical severity due to its network accessibility, low attack complexity, lack of required privileges or user interaction, scope change, high confidentiality impact, and low integrity impact.
An unauthorized attacker can exploit this vulnerability remotely over the network without authentication, privileges, or user interaction. Successful exploitation allows the attacker to inject malicious commands, resulting in the disclosure of sensitive information, with potential for limited integrity modifications due to the changed scope.
The Microsoft Security Response Center (MSRC) provides details on this vulnerability, including update guidance, at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-59252.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-33549
Vulnerability details
Improper neutralization of special elements used in a command ('command injection') in Copilot allows an unauthorized attacker to disclose information over a network.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Enterprise AI Assistants
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: copilot
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Command injection (CWE-77) in a network-accessible service (Copilot) directly enables remote exploitation of public-facing apps (T1190) and arbitrary command execution (T1059).
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
SI-10 mandates information input validation at entry points, directly neutralizing special elements to prevent command injection exploitation in Copilot.
SI-2 requires timely identification, reporting, and correction of flaws like CVE-2025-59252, preventing remote unauthorized command injection and information disclosure.
SC-2 enforces separation of user and system functionality, blocking user-supplied inputs from interfering with command execution and mitigating injection attacks.