Cyber Resilience

CVE-2026-48561

RCE in Microsoft 365 Copilot

Published
14 July 2026
Modified
26 July 2026
Patch / advisory
CVSS Score v3.1 9.6
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
EPSS Score 0.0076 52th percentile
Risk Priority 70 floored blend · peak EPSS

Summary

CVE-2026-48561 is a critical-severity Command Injection (CWE-77) vulnerability in Microsoft 365 Copilot. Its CVSS base score is 9.6 (Critical).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 48% 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.

The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) and AC-6 (Least Privilege) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

Improper neutralization of special elements used in a command ('command injection') in Copilot Chat (Microsoft Edge) allows an unauthorized attacker to execute code over a network.

CWE(s)

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: copilot

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
Why these techniques?

Command injection (CWE-77) in network-exposed Microsoft Copilot directly enables remote code execution against a public-facing application (T1190).

Confidence: HIGH · MITRE ATT&CK Enterprise v19.0

CVEs Like This One

CVE-2026-42895Same product: Microsoft 365 Copilot
CVE-2026-24299Same product: Microsoft 365 Copilot
CVE-2026-42827Same product: Microsoft 365 Copilot
CVE-2026-41090Same product: Microsoft 365 Copilot
CVE-2026-42824Same vendor: Microsoft
CVE-2026-26133Same product: Microsoft 365 Copilot
CVE-2025-59272Same vendor: Microsoft
CVE-2025-59252Same vendor: Microsoft
CVE-2026-21520Same vendor: Microsoft
CVE-2026-23653Same vendor: Microsoft

Affected Assets

microsoft
365 copilot
all versions

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)
  • SI-10 Information Input Validation
  • AC-6 Least Privilege
  • SI-2 Flaw Remediation
Detect
Catch it (NIST detect / respond)
  • SI-2 Flaw Remediation
Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.2.3
  • V1.2.5
  • V1.2.8
  • V1.2.9

Mitigating Controls (NIST 800-53 r5) AI

prevent

Directly requires validation and neutralization of untrusted input to block command injection payloads before they reach the Copilot Chat interpreter.

prevent

Enforces least privilege on the Edge/Copilot process so that even a successful command injection yields minimal system impact.

preventrespond

Mandates prompt application of vendor patches that remediate the CWE-77 flaw in Copilot Chat.

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.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require input validation and neutralization that prevent command injection.

DE.CM-09 partial match
prevents

Runtime monitoring of software and data can detect anomalous command execution resulting from injection.

ID.RA-01 partial match
prevents

Identifying recorded vulnerabilities enables remediation of command-injection flaws before exploitation.

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.

prevents

Secure coding standards require proper escaping and parameterization of commands, directly eliminating CWE-77.

detects

Security testing in development catches command-injection vulnerabilities before release.

prevents

Secure development life cycle mandates input validation and command construction practices that directly prevent command injection.

prevents

Application security requirements explicitly call for controls against injection flaws including command injection.

prevents

Secure architecture principles reduce the attack surface but do not prescribe the specific neutralization techniques needed.

none

Environment separation limits the blast radius of an exploited command injection but does not prevent the flaw itself.

References