Work-data disclosure via indirect prompt injection
Published Jun 11, 2025 · Updated Feb 26, 2026
AI command injection in Microsoft 365 Copilot allows remote attackers to disclose work data through a crafted email. A hidden prompt in the email is ingested as trusted context, directs Copilot to retrieve other Microsoft 365 data, and embeds it in an external image URL fetched through a trusted Teams proxy. No click or direct interaction with the malicious email is required; disclosure occurs when Copilot processes it during a later user query and is limited to data available in that user’s context.
Summary
What happened
AI command injection in Microsoft 365 Copilot allows remote attackers to disclose work data through a crafted email. A hidden prompt in the email is ingested as trusted context, directs Copilot to retrieve other Microsoft 365 data, and embeds it in an external image URL fetched through a trusted Teams proxy. No click or direct interaction with the malicious email is required; disclosure occurs when Copilot processes it during a later user query and is limited to data available in that user’s context.
The record
- CVE
- CVE-2025-32711
- Published
- Jun 11, 2025
- Updated
- Feb 26, 2026
- Vendor
- Microsoft
- Product
- Microsoft 365 Copilot
- Classifications
- CWE-74, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 11, 2025CVE publishedPublication date reported by the CVE source.
- Feb 26, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=-
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- EchoLeak technical proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo