CVE-2025-32711
Microsoft 365 Copilot
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:NSummary
CVE-2025-32711 is a critical-severity Injection (CWE-74) vulnerability in Microsoft 365 Copilot. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 6% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2025-32711 is an AI command injection vulnerability in Microsoft 365 Copilot that is tracked under CWE-74. The flaw permits unauthorized information disclosure across a network and carries a CVSS 3.1 score of 9.3, reflecting network attack vector, low attack complexity, no required privileges or user interaction, and changed scope with high confidentiality impact.
An unauthenticated attacker can send crafted inputs over the network to trigger the command injection and obtain sensitive data from the affected M365 Copilot deployment. The published EPSS score of 0.1940 indicates moderate exploitation probability with no material rise observed after disclosure.
Microsoft has published an advisory at the Microsoft Security Response Center that addresses the issue, and additional technical analysis is available from AIM Security. The vulnerability’s occurrence in an AI-driven productivity service underscores risks specific to command handling within large language model integrations.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-18114
Vulnerability Data
Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.
- CWE(s)
AI Security AnalysisAI
- AI Category
- Enterprise AI Assistants
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- AI-specific weaknesses CR
- CWE-1427 — Untrusted input reaches LLM prompt in Copilot, enabling command injection/info disclosure.
Mapped by Cyber Resilience · not in NVD. Poisoning and extraction cases are routed to MITRE ATLAS instead of a synthetic CWE.- Classification Reason
- Matched keywords: ai, m365 copilot
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.1V1.2.3V1.2.5V1.2.8
Mitigating Controls (NIST 800-53 r5) AI
SI-10 directly requires validation of information inputs to reject malformed or special-element content before it reaches downstream parsers.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly require input validation and output encoding that prevent injection flaws.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development catches injection vulnerabilities before release.
Logging supports detection of injection attempts but does not prevent the weakness.
Monitoring activities can identify active injection attacks after they occur.
Secure development life cycle mandates input validation and output encoding that directly prevent injection flaws.
Application security requirements explicitly call for controls against injection attacks in software design.
Secure architecture principles reduce injection surfaces but do not prescribe specific neutralization techniques.