Loading story…
Microsoft disclosed CVE-2025-32711, a critical information disclosure flaw in Microsoft 365 Copilot that researchers later detailed as EchoLeak, describing it as the first reported real-world zero-click prompt injection exploit in a production LLM system. The vulnerability carried a CVSS 9.3 rating and allowed a remote, unauthenticated attacker to exfiltrate sensitive data over the network without user interaction, reportedly by sending a single crafted email that Copilot would process.
Research describing the exploit said the attack chained multiple bypasses across LLM trust boundaries, including evasion of Microsoft’s XPIA classifier, use of reference-style Markdown to bypass link redaction, auto-fetched images, and abuse of a Microsoft Teams proxy allowed by content security policy to extract data. Microsoft said the issue had already been fully mitigated in the cloud service and required no customer action, while the broader research and follow-on reporting framed the incident as evidence that prompt injection and "AIjacking" can enable full data exfiltration in enterprise copilots unless controls such as prompt partitioning, stronger filtering, provenance-based access control, stricter CSPs, least privilege, and continuous adversarial testing are in place.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
4 events from the most recent confirmed update back to the earliest known activity.
Microsoft last updated the CVE-2025-32711 advisory to revise the CWE classification, describing the change as informational rather than a new security development.
Public reporting and research descriptions outlined how EchoLeak chained multiple bypasses, including evasion of Microsoft's XPIA classifier, Markdown-based link redaction bypass, auto-fetched images, and abuse of a Microsoft Teams proxy allowed by content security policy.
Microsoft published advisory CVE-2025-32711 for a critical M365 Copilot information disclosure vulnerability caused by AI command injection. The company said the issue had already been fully mitigated, required no customer action, and that it had seen no evidence of in-the-wild exploitation at disclosure.
Security researchers discovered EchoLeak, later assigned CVE-2025-32711, a zero-click prompt injection vulnerability in Microsoft 365 Copilot that could enable remote, unauthenticated data exfiltration via a crafted email.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
4 references tracked. Mallory keeps watching after this page renders.
labs.zenity.io
Open sourcearxiv.org
Open sourcesimonwillison.net
Open sourcemsrc.microsoft.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Varonis Threat Labs disclosed **SearchLeak**, a critical exploit chain in Microsoft 365 Copilot Enterprise Search that could let an attacker steal sensitive enterprise data after a user clicked a single trusted `microsoft.com` link. Microsoft tracked the issue as **`CVE-2026-42824`** and remediated it on the backend. According to the researchers, the attack could expose data available through the victim’s Microsoft Graph permissions, including emails, calendar entries, meeting notes, SharePoint content, OneDrive files, and potentially MFA-related messages, though no in-the-wild exploitation was reported. The technique chained three weaknesses: **parameter-to-prompt injection** through the Copilot Search `q` parameter, an **HTML streaming race condition** that allowed an injected image tag to render before sanitization, and abuse of a **Bing allowlist** in Content Security Policy to exfiltrate the retrieved data through Bing’s server-side image fetch behavior. Researchers said the attack required no plugins, elevated privileges, or second user interaction, highlighting how AI prompt injection can revive older web security flaws in enterprise platforms. Microsoft rated the flaw critical, while public severity scoring differed across sources, and defenders were advised to watch for suspicious Copilot Search URLs containing encoded or HTML payloads and unusual Bing image endpoint traffic.
Jun 29, 2026
Researchers reported that vulnerabilities in Microsoft 365 Copilot and Consumer Copilot allowed attackers to turn prompt injection into data exfiltration, memory poisoning, and persistent compromise. Microsoft assigned `CVE-2026-24299` to the main issue set and rolled out fixes across late 2025 and early 2026, while a related Microsoft Excel flaw, `CVE-2026-26144`, showed how a conventional application bug could be chained with Copilot Agent mode to silently extract spreadsheet data. In the Copilot attacks, malicious content abused HTML preview rendering to leak sensitive information through external requests, first with CSS background images and later with `@font-face`, and researchers said users could be coerced into triggering the preview during normal interaction, creating a near zero-click exfiltration path. The research also showed that Copilot’s memory features could be poisoned to add or delete stored facts and implant persistent instructions that altered future sessions, enabling a backdoor dubbed **SpAIware** that continued leaking secrets over time. Similar issues were described in consumer Copilot, including durable-memory manipulation and browser-navigation exfiltration through Edge-integrated tooling. The findings underscore a broader security shift: AI assistants can collapse trust boundaries inside host applications, raising the impact of older flaws and forcing defenders to reassess assistant permissions, restrict outbound network access from AI-enabled apps, and separately monitor AI-initiated network activity.
Jun 29, 2026
Researchers at **Permiso Security** disclosed a **cross-prompt injection** weakness in **Microsoft 365 Copilot** email/Teams summarization features, tracked as **CVE-2026-26133**, that could let attackers embed instruction-like text inside a normal email and influence Copilot’s generated summary. The reported impact is the ability to produce **attacker-authored, convincing phishing content** inside Copilot’s *trusted* summarization UI—without attachments, macros, or traditional exploit code—by exploiting a trust-boundary failure where the model treats untrusted email content as instructions. Microsoft confirmed the issue and rolled out mitigations and a patch across affected surfaces, crediting **Andi Ahmeti** for the discovery. In parallel, Microsoft published operational guidance on **detecting and responding to prompt abuse** in AI tools, emphasizing that prompt injection/abuse is a leading LLM application risk (aligned with **OWASP** guidance) and that detection is difficult without strong **logging and telemetry**. The guidance describes common prompt-abuse patterns (including indirect prompt injection) and provides a practical playbook for investigation and response. A separate Praetorian post provides general AI security best practices (e.g., input validation, monitoring, and human oversight) but does not add incident-specific details about CVE-2026-26133.
Jun 29, 2026