Vulnerability

Copilot Vulnerability Breaks Audit Logs and Access Files Secretly for Hackers

A significant security vulnerability has been discovered in Microsoft’s Copilot for M365 that allowed users, including potential malicious insiders, to access and interact with sensitive files without leaving any record in the official audit logs.

After patching the flaw, Microsoft has reportedly decided against issuing a formal CVE or notifying its customers, leaving organizations unaware that their security logs from before the fix may be critically incomplete.

The vulnerability, detailed by a security researcher at the tech company Pistachio, was remarkably simple to exploit.

Under normal circumstances, when a user asks Copilot to summarize a file, the action is recorded in the M365 audit log, a crucial feature for security monitoring and compliance.

Copilot output with Audit Log (Source: Pistachio)
Copilot output with Audit Log (Source: Pistachio)

However, the researcher found that by simply adding a command for Copilot not to provide a reference link to the summarized file, the AI assistant would act without triggering any log entry.

Copilot output without Audit Log (Source: Pistachio)

This effectively creates a digital blind spot for security teams. A malicious employee could use this method to access and exfiltrate confidential data, intellectual property, or personal information right before leaving a company, all without a trace.

For organizations in regulated industries like healthcare and finance, which rely on the integrity of audit logs to meet compliance standards like HIPAA, the implications are severe.

The researcher who discovered the flaw on July 4, 2025, described a “frustrating and opaque” disclosure process with the Microsoft Security Response Center (MSRC).

Despite Microsoft’s public guidelines for vulnerability reporting, the researcher claims the company silently began patching the issue before officially acknowledging it and failed to communicate clearly.

Microsoft ultimately classified the vulnerability as “Important” and deployed a fix on August 17. However, the company informed the researcher that a CVE would not be issued because the fix was pushed automatically to users without requiring manual updates. This justification contradicts Microsoft’s own policy, which does not state that automatic updates preclude a CVE.

Furthermore, Microsoft confirmed it has no plans for public disclosure. This decision has drawn sharp criticism, as it means customers are not being informed that their audit logs from prior to August 18 may be unreliable.

The ease of exploitation suggests that the vulnerability could have been triggered unintentionally by regular users, meaning countless organizations could have compromised logs without knowing.

Adding to the concern, it was later revealed that this was not the first time the vulnerability had been found. Michael Bargury, CTO at the security firm Zenity, reportedly discovered and disclosed the exact same issue over a year ago, yet it remained unpatched.

While the vulnerability is now fixed, a critical gap remains. For an indeterminate period, any organization using M365 Copilot may have incomplete audit records, undermining security investigations and regulatory compliance.

Microsoft’s decision to handle the issue silently raises serious questions about its commitment to transparency as it rapidly integrates AI across its product ecosystem.

Safely detonate suspicious files to uncover threats, enrich your investigations, and cut incident response time. Start with an ANYRUN sandbox trial → 

Guru Baran

Gurubaran KS is a cybersecurity analyst, and Journalist with a strong focus on emerging threats and digital defense strategies. He is the Co-Founder and Editor-in-Chief of Cyber Security News, where he leads editorial coverage on global cybersecurity developments.

Recent Posts

Google Chrome 153 Update Fixes 42 Security Flaws, Including 3 Critical Ones

Google has released an important Chrome 153 security update that fixes 42 vulnerabilities across the…

30 minutes ago

CISA and NIST Release Technical Checklist for Safeguarding Identity Tokens From Theft and Misuse

The Cybersecurity and Infrastructure Security Agency (CISA) and the National Institute of Standards and Technology…

10 hours ago

CISA Shares 17 Techniques Used by Hackers to Compromise Active Directory Environments

CISA and five international cybersecurity agencies have released detailed guidance describing 17 common techniques hackers…

11 hours ago

Apple Rolls Out Massive Security Update Fixing 273 Vulnerabilities Across Its Devices

Apple has released one of its largest coordinated security rollouts, addressing 273 distinct critical vulnerabilities…

12 hours ago

How to Keep Malware’s Rotating Infrastructure From Becoming a Detection Gap

You can’t detect today's attacks with yesterday’s threat intelligence; that’s how you could briefly formulate…

12 hours ago

Microsoft Bans Its AI Models From Launching Cyberattacks or Escalating Their Own Access

Microsoft has published a draft Humanist AI Code of Conduct that would prohibit its in-house…

12 hours ago