LiveActive security incident?Get immediate response
CVE Record

CVE-2026-26133: M365 Copilot Information Disclosure Vulnerability

AI command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.

HighCVSS 7.1Not KEV-listedUpdated
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

CVE-2026-26133 is a Microsoft 365 Copilot information disclosure issue caused by AI command injection. A remote unauthenticated attacker could cause Copilot-related clients to reveal information if user interaction occurs. The business concern is potential exposure of sensitive Microsoft 365 data through affected apps.

Executive priority

High priority for Microsoft 365-heavy organizations, especially where Copilot can access sensitive mail, files, chats, notebooks, or reports. Patch verification should be handled promptly, but the provided evidence does not support emergency active-exploitation language.

Technical view

The source describes AI command injection mapped to CWE-77. CVSS 3.1 is 7.1: network exploitable, low complexity, no privileges required, user interaction required, high confidentiality impact, low integrity impact, and no availability impact. Microsoft lists an official remediation through MSRC.

Likely exposure

Exposure is most likely where users run affected Microsoft 365 Copilot, Office, Edge, Teams, Outlook, Power BI, Loop, or OneNote clients on Android, iOS, or Outlook for Mac. Prioritize environments with Copilot access to sensitive mail, files, chats, notebooks, or BI content.

Exploitation context

The bundle does not show CISA KEV listing or confirmed active exploitation. The CVSS vector marks exploit maturity as unproven and requires user interaction. Treat exploitation as plausible but not confirmed from the provided sources.

Researcher notes

Key constraints are user interaction and information disclosure, with no availability impact. The affected product list is broad across Microsoft mobile clients and Outlook for Mac. The bundle does not include technical exploit details, attack primitives, or precise fixed versions beyond the MSRC advisory reference.

Mitigation direction

  • Review the Microsoft MSRC advisory for the official fix and affected product details.
  • Update affected Microsoft mobile and Mac clients according to Microsoft guidance.
  • Prioritize users with Copilot access to sensitive Microsoft 365 data.
  • Limit Copilot access where business need is unclear until updates are verified.
  • Monitor Microsoft 365 audit logs for unusual data access or sharing patterns.

Validation and detection

  • Inventory affected Microsoft 365 apps on Android, iOS, and Outlook for Mac.
  • Confirm installed app versions against Microsoft’s advisory and update channels.
  • Identify users licensed for Copilot and map their sensitive data access.
  • Check mobile device management compliance for required app update status.
  • Review security monitoring for abnormal Copilot-adjacent access events.
Prepared
Confidence
medium
Sources
3

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-77: Command execution behavior lookup

Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Execution behavior lookup

The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-26133 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
7.1 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N/E:U/RL:O/RC:C

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

1CVSS vectors
3Timeline events
1ADP providers
2Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: partial

CVSS vector scores

1 official score

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
7.1CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N/E:U/RL:O/RC:C2.84.2microsoft

Vulnerability scoring details

Base CVSS 3.1 score

7.1High
CVSS 3.1 vector shape for CVE-2026-26133Attack VectorAttack ComplexityPrivileges RequiredUser InteractionScopeConfidentiality ImpactIntegrity ImpactAvailability Impact

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:L/A:N/E:U/RL:O/RC:C

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Privileges Required
NoneLowHigh
User Interaction
NoneRequired
Scope
ChangedUnchanged
Confidentiality Impact
HighLowNone
Integrity Impact
HighLowNone
Availability Impact
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. CVE publishedCVE Program

    The CVE record was published.

  3. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
MicrosoftMicrosoft 365 Copilot for Android1.0Listed
MicrosoftMicrosoft 365 Copilot for iOS1.0Listed
MicrosoftMicrosoft Edge for Android1.0.0Listed
MicrosoftMicrosoft Edge for iOS1.0.0.0Listed
MicrosoftMicrosoft Excel for Android16.0.0.0Listed
MicrosoftMicrosoft Excel for iOS1.0Listed
MicrosoftMicrosoft Loop for iOS2.0.0Listed
MicrosoftMicrosoft OneNote1.0.0Listed
MicrosoftMicrosoft OneNote for Android16.0.1Listed
MicrosoftMicrosoft Outlook for Android1.0Listed
MicrosoftMicrosoft Outlook for iOS1.0.0Listed
MicrosoftMicrosoft Outlook for Mac1.0.0Listed
MicrosoftMicrosoft PowerBI for Android2.0.0Listed
MicrosoftMicrosoft PowerBI for iOS1.0.0Listed
MicrosoftMicrosoft PowerPoint for Android16.0.0.0Listed
MicrosoftMicrosoft PowerPoint for iOS1.0Listed
MicrosoftMicrosoft Teams for Android1.0.0Listed
MicrosoftMicrosoft Teams for iOS2.0.0Listed
MicrosoftMicrosoft Word for Android16.0.0.0Listed
MicrosoftMicrosoft Word for iOS2.0.0Listed
Weakness

CWE details

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.

CWE-77 · source CWE mapping

Improper Neutralization of Special Elements used in a Command ('Command Injection')

Improper Neutralization of Special Elements used in a Command ('Command Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.