Information disclosure via AI command injection
Published Mar 13, 2026 · Updated Mar 13, 2026
AI command injection in Microsoft 365 Copilot clients allows remote attackers to disclose information through attacker-supplied content. Microsoft identifies the flaw only as AI command injection and has not published the affected Copilot processing locus or the operation that treats untrusted content as commands. Exploitation requires user interaction but no prior privileges; disclosed impacts are information exposure and limited integrity loss, with no availability impact.
Summary
What happened
AI command injection in Microsoft 365 Copilot clients allows remote attackers to disclose information through attacker-supplied content. Microsoft identifies the flaw only as AI command injection and has not published the affected Copilot processing locus or the operation that treats untrusted content as commands. Exploitation requires user interaction but no prior privileges; disclosed impacts are information exposure and limited integrity loss, with no availability impact.
The record
- CVE
- CVE-2026-26133
- Published
- Mar 13, 2026
- Updated
- Mar 13, 2026
- Vendor
- Microsoft
- Product
- Microsoft PowerPoint for Android
- Classifications
- CWE-77
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 13, 2026CVE publishedPublication date reported by the CVE source.
- Mar 13, 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=16.0.0.0 <16.0.19822.20038
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
No public exploit references are available in this record.
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