- ID
- AIA-003
- Category
- AI AI agent incident
- Disclosed
- 2025-06
- Systems
- Microsoft 365 Copilot
- Harm type
- Data leak / prompt injection
- Status
- confirmed by vendor
Microsoft published CVE-2025-32711. - CVE
CVE-2025-32711- CISA KEV
- Not in CISA KEV as of catalog 2026.10.30
Checked 2026-10-31 against catalog 2026.10.30
Summary
Microsoft published CVE-2025-32711, rated Critical: "Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network."
Controls
Controls that could prevent, detect, or support recovery from this kind of failure. Mappings are editorial judgments made by the method, not findings about what any party should have done.
NIST AI RMF
- MEASURE 2.7 Security and resilience are evaluated and documented
- MANAGE 4.1 Post-deployment monitoring is in place
NIST SP 800-53
- AC-4 Information Flow Enforcement
- SI-10 Information Input Validation
- SC-7 Boundary Protection
- SI-2 Flaw Remediation
Human-approval (JCR) checkpoint
Sources
- msrc.microsoft.com primary link checked 2026-10-31, HTTP 200
Released Jun 11, 2025; last updated Feb 20, 2026
https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-32711
Corrections
- Verification round 1: date month confirmed (MSRC released Jun 11, 2025). Dropped "EchoLeak", "zero-click", the crafted-email detail and the Aim Security attribution from title and summary: the cited MSRC page does not mention them and no Aim Security source has been fetched.
To report an error in this entry, see corrections.