CVE-2025-32711
M365 Copilot Information Disclosure Vulnerability
Exploitation likely. EPSS gives it a 9.3% chance of exploitation in the next 30 days. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
Coverage timeline
4 publishersESET highlighted rising cybersecurity risks for SMBs adopting AI agents, noting thousands of malicious skills discovered in repositories that enable credential theft, data exfiltration, and remote code execution through compromised supply c
New 'agent data injection' technique exploits trusted AI agent inputs, causing unintended actions like fake clicks or command execution.
Vendor patch released
Sourced from public security reporting — each date is when it was published, not when it happened. 1 further article named this CVE in wider roundups without reporting it as a distinct event.
What it is
From the CVE record
Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
9.3% chance of exploitation activity in the next 30 days, which ranks it in the 95th percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
7 events over 376 days, from the signal feeds we watch.
- EPSS band changemoderate → low
- EPSS band changelow → moderate
- Patch availablerecord updated
- Publishedweakness classified, att&ck mapped
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
Scored 9.3 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity LowNo special conditions — the attack can be reliably reproduced
- Privileges Required NoneNo authentication required — anyone can exploit this
- User Interaction NoneNo user interaction needed — fully automated exploitation
Scope
- Scope ChangedThe exploit can affect other components (e.g. sandbox escape, host compromise from VM)
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity LowData modification is possible but limited in scope or consequence
- Availability NoneNo availability impact
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
Sources
References in the record
- msrc.microsoft.com/update-guide/vulnerability/CVE-2025-32711
- aim.security/lp/aim-labs-echoleak-m365
- msrc.microsoft.com/update-guide/vulnerability/CVE-2025-32711&
And 1 more reference. See all after sign-in
In the news
- The SMB cybersecurity squeeze: AI agents at work, old attacks in overdrive
- New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands
- New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email
- AI как новая поверхность атаки: реальные инциденты, мошенничество и уязвимости агентной эпохи
- Prompt injection нельзя запатчить: год «летальной триады» и лента CVE 2026 года
- One-Click Microsoft 365 Copilot Flaw Could Have Let Attackers Steal Emails, Files, and MFA Codes
- Otto Support - Logging and Visibility in MCP Servers
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for 365 Copilot, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI