CVE-2025-59286
Published: 09 October 2025
Summary
CVE-2025-59286 is a critical-severity Command Injection (CWE-77) vulnerability in Microsoft 365 Copilot Chat. 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 SI-10 (Information Input Validation) and SI-2 (Flaw Remediation).
Deeper analysis
CVE-2025-59286 is a command injection vulnerability (CWE-77) in Copilot due to improper neutralization of special elements used in a command. Published on 2025-10-09, it carries 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), marking it as critical severity with network accessibility, low complexity, no privileges or user interaction required, changed scope, high confidentiality impact, low integrity impact, and no availability impact.
An unauthorized attacker can exploit this vulnerability over the network without authentication or user interaction. Successful exploitation allows disclosure of information, enabling remote data exfiltration with potential minor integrity alterations due to the command injection.
The Microsoft Security Response Center advisory at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-59286 provides details on patches and mitigation recommendations.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-33546
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 in a network-accessible Copilot component directly enables remote exploitation of public-facing apps (T1190) and arbitrary command execution via interpreters (T1059).
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
SI-10 directly and comprehensively prevents command injection by validating and neutralizing special elements in inputs to Copilot.
SI-2 ensures timely remediation of the specific command injection flaw in CVE-2025-59286 through patching as advised by MSRC.
SI-9 restricts information inputs to Copilot, limiting opportunities for special elements that enable command injection.