Skip to content
Registry/APM-0071
APM-00714SEVEREReported June 11, 2025

'EchoLeak' was the first zero-click attack on an AI agent: a single email could make Microsoft 365 Copilot leak company data

Agent Involved
Microsoft 365 Copilot
Estimated Damage
Not quantified
Severity
4 / 5 Severe
Impact Band
Serious damage. Customer data affected, security incident, or financial losses $10k–$100k.

Independent project · aggregated from public reports and may be unverified — see the primary source below · not affiliated with or endorsed by any company or product named.

Disclosed in June 2025, EchoLeak (CVE-2025-32711, CVSS 9.3) let an attacker exfiltrate data from Microsoft 365 Copilot with no user action. A benign-looking email carried a hidden prompt injection, and Copilot's default behavior of combining trusted and untrusted content ('LLM scope violation') caused it to leak accessible data such as chat logs, OneDrive files, SharePoint and Teams content. Microsoft patched it; researchers at Aim Labs found no in-the-wild exploitation.

Verified Facts

  • EchoLeak (CVE-2025-32711) is a zero-click flaw in Microsoft 365 Copilot, CVSS 9.3
  • A hidden prompt injection in an email could make Copilot leak accessible enterprise data
  • Microsoft patched it and reported no evidence of in-the-wild exploitation

Not Publicly Confirmed

  • Whether similar scope-violation bugs remain in other AI assistants

Operational Lessons

  • An agent that mixes trusted and untrusted content without isolation can be turned into a data-leak vector
  • Prompt injection is a security vulnerability class, not just a content problem
Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction (The Hacker News)thehackernews.com
Case No.
APM-0071
Reported
June 11, 2025
Attribution
Anonymous
Discussion

More Cases

0
APM-0083Cursor3MODERATE
Jan 14, 2026

Cursor's command allowlist could be bypassed with shell built-ins, giving prompt injection a silent path to code execution

Pillar Security disclosed CVE-2026-22708 in Cursor. In Auto-Run Mode with an allowlist enabled, shell built-ins such as export, typeset, declare, readonly, unset and local were implicitly trusted by Cursor's server-side evaluator and executed without appearing in the allowlist or requiring approval, because they run inside the shell session rather than as separate binaries. An attacker delivering indirect prompt injection could silently poison environment variables and then trigger malicious code through trusted developer tools, producing both zero-click and one-click remote code execution. Pillar reported it in August 2025, Cursor acknowledged it as a systemic issue in September 2025, and the fix shipped in version 2.3 in January 2026, which now requires explicit approval for any command the parser cannot classify.

0
May 7, 2026

Prompt injection reached host-level code execution in Microsoft Semantic Kernel through eval() and a stray annotation

Microsoft disclosed two vulnerabilities that turn prompt injection into host compromise in its Semantic Kernel agent framework, which has over 27,000 GitHub stars. CVE-2026-26030 affects the Python package before 1.39.4: the default in-memory vector store filter is a Python lambda executed with eval() on unsanitized model-controlled input, so an attacker could escape the template string, traverse Python's class hierarchy, bypass the AST blocklist validator and run arbitrary commands, demonstrated by launching calc.exe from a single prompt injection. CVE-2026-25592 affects the .NET SDK before 1.71.0: DownloadFileAsync was accidentally marked with a [KernelFunction] attribute, exposing it to the model with an entirely AI-controlled, unvalidated local file path, allowing writes to locations such as the Windows Startup folder and thus sandbox escape.

0
APM-0080Microsoft 365 Copilot4SEVERE
Jun 15, 2026

SearchLeak let a single click on a malicious link pull emails, files and MFA codes out of Microsoft 365 Copilot

Varonis Threat Labs disclosed CVE-2026-42824, a critical flaw in Microsoft 365 Copilot Enterprise Search. Clicking a single crafted link chained three bugs: injection of the URL parameter into the prompt, a rendering race condition, and abuse of Content Security Policy allowlisting to exfiltrate data through Bing's infrastructure. The attack could reach emails and calendar details, indexed SharePoint and OneDrive files, one-time and MFA codes, password-reset links, meeting notes and salary data. Because Copilot Enterprise is a managed service, tenant admins could not patch it themselves; Microsoft mitigated the flaw on its backend.