CVE-2025-59252: Microsoft 365 Word Copilot · Command Injection
Affects Microsoft 365 Word CopilotSource CVE Database V5
Not known to be exploited · CVSS 9.3 Critical.
Data as of 26 Oct 2026, 08:30 UTC
- EPSS
- 0.5% chance of exploitation in 30 days – higher than 46% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N/E:U/RL:O/RC:CExploitation evidence
Disclosed: evidence found.
CVE published 9 Oct 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.
What to do
AI-suggested
Organizations should monitor Microsoft security advisories closely and apply patches or updates for Microsoft 365 Word Copilot as soon as they become available. In the interim, network-level defenses such as intrusion detection and prevention systems (IDS/IPS) should be configured to detect and block anomalous command injection patterns targeting Word Copilot. Restricting network access to Microsoft 365 services to trusted IP ranges and enforcing strict egress filtering can reduce exposure. Employing application-layer firewalls and enabling advanced threat protection features within Microsoft 365 can help identify suspicious activities. Administrators should audit and limit permissions related to document automation and AI features to minimize potential exploitation scope. User education on recognizing unusual document behavior and reporting anomalies can aid early detection. Finally, organizations should implement robust logging and monitoring of Microsoft 365 activities to facilitate rapid incident response if exploitation attempts occur.
Description
Improper neutralization of special elements used in a command ('command injection') in Copilot allows an unauthorized attacker to disclose information over a network.