Skip to content
OpenAdvisories
Critical · 9.3 Public exploit CVE-2025-32711 EUVD-2025-18114GHSA-h2w9-p5qf-qmrh

M365 Copilot Information Disclosure Vulnerability

Published Jun 11, 2025 · Updated Nov 3, 2026 · Assigned by microsoft

Description

Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network.

Affected products

VendorProductAffectedFixed
Microsoft Microsoft 365 Copilot - —

Public exploits

Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.

Third-party code, not reviewed by us. Public PoCs are sometimes fake or contain malware. Read the code first and run it only in an isolated lab, against systems you are authorised to test.

GitHub 5 repositories

  • vikasudasi/exfil-scan ★ 6 · Jul 25, 2026

    Scan LLM outputs and AI-generated content for data exfiltration signals (EchoLeak, CVE-2025-32711) before they reach users or downstream systems

  • daryllundy/cve-2025-32711 ★ 3 · Jun 27, 2025

    Proof-of-concept and analysis for CVE-2025-32711

  • Threat hunt reconstructing an M365 Copilot indirect prompt injection (CVE-2025-32711 "EchoLeak"): poisoned email attachment, Graph API data collection, markdown-image exfiltration, and system prompt …

  • AISec Plus Week 1 threat write-up — EchoLeak (CVE-2025-32711), zero-click indirect prompt injection in Microsoft 365 Copilot.

  • TreRB/markdown-exfil-tester ★ 0 · Apr 20, 2026

    Black-box test whether an LLM chatbot is vulnerable to markdown/HTML exfil (CVE-2025-32711 class). Spins up a sink, sends payloads, renders in headless Chromium, correlates via network.

Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.

Advisories 2

References