Browse / Direct Prompt Injection / AML.CS0059
EchoLeak: Zero-Click Prompt Injection Targeting M365 Copilot for Data Exfiltration
- Technique
- LLM Prompt Crafting
- Target
- Microsoft 365 Copilot (Exercise)
How it worked
- AI Attack Adaptation · LLM Prompt Crafting
The researchers crafted malicious instructions designed to evade Microsoft's indirect prompt injection classifier, appear like ordinary business content, suppress attribution to the attacker-controlled email, and cause Copilot to include sensitive data in rendered output.
- AI Attack Adaptation · Retrieval Content Crafting
The researchers embedded the prompt injection in business-like email content that was likely to be retrieved during a later Copilot interaction. The content was designed to appear relevant to ordinary enterprise workflows while carrying hidden instructions.
- Resource Development · Stage Capabilities
The researchers staged an attacker-controlled web endpoint to receive outbound requests containing encoded sensitive data. The endpoint served as the collection point for the exfiltration channel.
- Initial Access · Prompt Infiltration via Public-Facing Application
The researchers sent the email to a Microsoft 365 user inbox.
- Defense Evasion · LLM Prompt Obfuscation
The prompt was phrased as benign business text rather than and obviously malicious prompt to evade user suspicion.
- Persistence · RAG Poisoning
The email was automatically ingested into a RAG database available to Copilot's retrieval pipeline.
- Execution · LLM Prompt Injection: Triggered
When the user later invoked Copilot, it retrieved the malicious email into its context and triggering the prompt injection.
- Collection · Data from AI Services: RAG Databases
The malicious instructions caused Copilot to access sensitive enterprise information available through the user's Microsoft 365 account, such as emails, files, or project details.
- Defense Evasion · LLM Trusted Output Components Manipulation
The output was manipulated to avoid obvious attribution and to use reference-style Markdown links or images that bypassed link redaction.
- Exfiltration · LLM Response Rendering
Copilot rendered a Markdown image whose URL encoded sensitive information. The client automatically attempted to fetch the image, creating a zero-click exfiltration path.
- Exfiltration · Exfiltration via Cyber Means
To bypass CSP restrictions, the researchers routed the rendered image request through an allowed Microsoft Teams preview or proxy path, which fetched the attacker-controlled URL containing the encoded secret.
- Impact · External Harms
If exploited against a real enterprise user, the attack could disclose confidential business data and harm the organization or affected users.
Summary
Aim Security researchers discovered EchoLeak, a zero-click vulnerability in Microsoft 365 Copilot that could allow an attacker to exfiltrate sensitive enterprise data without user interaction.
The attack used a prompt injection delivered via an email sent to a target user. When M365 Copilot retrieved the email as part of its retrieval-augmented generation (RAG) context, the malicious instructions caused Copilot to search the user's accessible Microsoft 365 data and include sensitive information in its response context. The sensitive information was then exfiltrated via requests to attacker-controlled URLs without requiring the victim to open the email or click a link.
The attack chain bypassed multiple protections, including prompt injection defenses, link redaction, and content security policy restrictions.
Microsoft assigned the issue CVE-2025-32711[[cve-2025-32711]]. It has since been remediated with no evidence it was exploited in the wild.
References
- https://arxiv.org/abs/2509.10540
- https://www.cve.org/CVERecord?id=CVE-2025-32711
- https://www.catonetworks.com/blog/breaking-down-echoleak/
Source: MITRE ATLAS case studies, used under Apache 2.0.