VulnerabilityPublished 11 Jun 2025Updated 26 Feb 2026

CVE-2025-32711: Microsoft 365 Copilot · Injection

Affects Microsoft 365 CopilotSource CVE Database V5

Not known to be exploited · CVSS 9.3 Critical.

Data as of 26 Oct 2026, 10:12 UTC

CVSS 3.1 base score

9.3Critical

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 9.2% chance of exploitation in 30 days – higher than 95% 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:C

Base metrics

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Changed
Confidentiality: High
Integrity: Low
Availability: None

Temporal metrics

Exploit Code Maturity: Unproven
Remediation Level: Official Fix
Report Confidence: Confirmed

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: None: There is no impact to availability within the impacted component.
Exploit Code Maturity: Unproven: No exploit code is available, or an exploit is theoretical.
Remediation Level: Official Fix: A complete vendor solution is available. Either the vendor has issued an official patch, or an upgrade is available.
Report Confidence: Confirmed: Detailed reports exist, or functional reproduction is possible (functional exploits may provide this). Source code is available to independently verify the assertions of the research, or the author or vendor of the affected code has confirmed the presence of the vulnerability.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 11 Jun 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.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

AI-suggested

Monitor Microsoft security advisories closely and apply official patches or updates for Microsoft 365 Copilot immediately upon release to remediate the vulnerability.
Implement strict input validation and output encoding mechanisms within any custom integrations or extensions interacting with Microsoft 365 Copilot to prevent injection of malicious commands or special characters.
Employ network segmentation and access controls to limit exposure of Microsoft 365 Copilot services to only trusted users and devices.
Use data loss prevention (DLP) tools to monitor and block unauthorized data exfiltration attempts originating from AI assistant interactions.
Conduct regular security assessments and penetration testing focused on AI and automation components to identify injection and other logic-based vulnerabilities.
Educate users and administrators about the risks of AI command injection and encourage reporting of suspicious AI assistant behavior.
Leverage Microsoft Defender and other endpoint detection and response (EDR) solutions to detect anomalous activities related to AI command injection attempts.
Review and harden downstream components that process AI output to ensure they properly sanitize and validate all inputs before execution or display.

Description

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

Impact

The primary impact of CVE-2025-32711 is the unauthorized disclosure of sensitive information, which can lead to severe confidentiality breaches for organizations using Microsoft 365 Copilot. Attackers exploiting this vulnerability can remotely extract data without authentication or user interaction, increasing the risk of data leaks, intellectual property theft, and exposure of personally identifiable information (PII). The integrity of data is only slightly affected, as the vulnerability mainly facilitates information disclosure rather than data modification. Availability is not impacted, so service disruption is unlikely. Organizations relying heavily on AI-assisted productivity tools may face reputational damage, regulatory penalties, and loss of customer trust if sensitive data is exposed. The vulnerability's network-based attack vector and low complexity make it attractive for attackers, potentially increasing the likelihood of exploitation once proof-of-concept or exploit code becomes available. Enterprises with extensive Microsoft 365 Copilot deployments, especially in regulated industries such as finance, healthcare, and government, are at heightened risk.

CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection') (opens in a new tab)
Class weaknessLikelihood of exploit: HighOWASP Top 10 A05:2025: Injection (opens in a new tab)
The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.
MITRE discourages mapping vulnerabilities to this broad entry; the root cause is usually a more specific weakness.
Requirements
Programming languages and supporting technologies might be chosen which are not subject to these issues.
Implementation
Utilize an appropriate mix of allowlist and denylist parsing to filter control-plane syntax from all input.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
Injection Prevention (opens in a new tab)
SQL Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
Attack patterns
Buffer Overflow via Environment Variables (opens in a new tab)
Server Side Include (SSI) Injection (opens in a new tab)
HTTP Request Splitting (opens in a new tab)
Command Line Execution through SQL Injection (opens in a new tab)
Double Encoding (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Description

AI analysisMachine-generated, updated 28 Feb 2026, 23:33 UTC

WeaknessesCWE-74

Technical details

References

Community reviews

Related threats