Cyber Resilience

CVE-2026-21521

Microsoft 365 Word Copilot

Published
22 January 2026
Modified
02 February 2026
Patch / advisory
CVSS Score v3.1 7.4
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:N/A:N
EPSS Score 0.0050 41th percentile
Risk Priority 54 floored blend · peak EPSS

Summary

CVE-2026-21521 is a high-severity Improper Neutralization of Escape, Meta, or Control Sequences (CWE-150) vulnerability in Microsoft 365 Word Copilot. Its CVSS base score is 7.4 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Content Injection (T1659); ranked at the 41th 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 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-2026-21521 is an improper neutralization of escape, meta, or control sequences vulnerability (CWE-150) affecting Copilot. Published on 2026-01-22, it carries a CVSS v3.1 base score of 7.4 (AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:N/A:N), indicating high severity due to network accessibility, low attack complexity, and significant confidentiality impact.

An unauthorized attacker with no privileges required can exploit this vulnerability remotely by inducing user interaction, such as clicking a malicious link or input. Successful exploitation changes the scope and enables disclosure of sensitive information over the network, with no impact on integrity or availability.

The Microsoft Security Response Center advisory at https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-21521 provides details on mitigation and patches.

EU & UK References

Vulnerability Data

Improper neutralization of escape, meta, or control sequences 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 Techniques

T1659 Content Injection Initial Access
Adversaries may gain access and continuously communicate with victims by injecting malicious content into systems through online network traffic.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-26149Same vendor: Microsoft
CVE-2023-40185Same vendor: Microsoft
CVE-2024-36052Same vendor: Microsoft
CVE-2026-47090Shared CWE-150
CVE-2024-49038Same vendor: Microsoft
CVE-2026-35651Shared CWE-150
CVE-2024-43610Same vendor: Microsoft
CVE-2025-65082Shared CWE-150
CVE-2023-39342Shared CWE-150
CVE-2024-38206Same vendor: Microsoft

Affected Assets

microsoft
365 word copilot
all versions

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.2.10
  • V1.3.12

Mitigating Controls (NIST 800-53 r5) AI

SI-10 requires validation/sanitization of inputs that directly stops escape/meta/control sequences from reaching downstream components.

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 neutralization and escaping to prevent this class of flaw.

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.

finds

Security testing can detect the weakness but does not itself implement neutralization.

prevents

Secure development lifecycle mandates input validation and output encoding that directly neutralizes escape/meta sequences.

prevents

Application security requirements explicitly call for controls against injection and malformed input sequences.

prevents

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

prevents

Secure coding standards require proper escaping and neutralization of control characters before downstream processing.

References