Loading story…
Security researchers disclosed attacks against Microsoft Copilot that use prompt injection and chained requests to extract sensitive data with minimal user interaction. Varonis Threat Labs described a single-click technique called Reprompt against Microsoft Copilot Personal that abuses legitimate Copilot links with a prefilled q parameter, then uses a double-request and chain-request flow to hide exfiltration instructions on an attacker-controlled server. The report said the attack could continue pulling data from an active session even after the Copilot tab was closed, while evading many client-side monitoring tools; Microsoft said the issue had been patched, and Varonis reported that Microsoft 365 Copilot enterprise customers were not affected.
A separate report from Rubrik Zero Labs said it had broken the Microsoft 365 Copilot sandbox in research published under the title ChatMate, indicating continued scrutiny of Copilot’s isolation and data-protection boundaries across Microsoft’s AI offerings. Together, the disclosures highlight how trusted Copilot workflows, prefilled prompts, and multi-step prompt handling can be abused to bypass intended safeguards and expose user data, reinforcing the need to treat AI prompt inputs and follow-on actions as untrusted.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
2 events from the most recent confirmed update back to the earliest known activity.
Microsoft confirmed the Reprompt issue had been patched by the time Varonis published its report. The write-up also states that Microsoft 365 Copilot enterprise customers were not affected.
Varonis Threat Labs uncovered an attack flow dubbed "Reprompt" in Microsoft Copilot Personal that uses legitimate Copilot links with prefilled prompts to enable one-click, stealthy data exfiltration. The report says the technique abuses the URL q parameter and chained follow-on requests to bypass Copilot safeguards.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
2 references tracked. Mallory keeps watching after this page renders.
Map 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 a prompt-injection attack chain dubbed **Reprompt** that enabled one-click data theft from **Microsoft Copilot** by abusing how Copilot accepts prompts via a URL. The technique relied on the `q` URL parameter to auto-populate and execute attacker-supplied instructions when a victim clicked a crafted Copilot link, requiring no plugins, connectors, or additional user-entered prompts. Researchers reported the method could expose sensitive information previously available in the Copilot session, including **PII**, and could continue exfiltration even after the Copilot chat window was closed. The reported attack flow chained multiple techniques to bypass Copilot’s protections, including **Parameter-to-Prompt (P2P) injection** via the `q` parameter and a **double-request bypass** in which safeguards applied to an initial request but could be defeated by forcing Copilot to repeat the task, leading to disclosure on a subsequent attempt. Varonis also described **chain-request exfiltration** to maintain covert control of the session and progressively extract data. Reporting indicates Microsoft took action in response to the research, though the core risk highlighted is that URL-triggered prompt execution and multi-step request chaining can undermine AI assistant guardrails if not consistently enforced across requests and session states.
Jun 29, 2026
Security researchers disclosed **Reprompt**, a single-click attack against **Microsoft Copilot Personal** that enabled stealthy exfiltration of sensitive user data by abusing a legitimate Copilot URL containing a malicious `q` parameter. After a victim clicks the link (typically delivered via phishing), the crafted URL triggers **Parameter-to-Prompt (P2P) injection**, auto-executing attacker-controlled prompts within the victim’s authenticated Copilot session; researchers reported the attacker can maintain control and continue querying data even after the Copilot window/tab is closed. Microsoft has **patched** the issue. Varonis Threat Labs described an attack chain that combines three techniques to bypass Copilot’s guardrails and evade detection: **P2P injection** (prompt injection via the `q` parameter on page load), **Double-Request** (leveraging the observation that leak protections may apply to the first request but not a repeated action), and **Chain-Request** (server-driven, sequential follow-up prompts that adapt based on prior responses). Reported exposed data includes **personally identifiable information (PII)** and other Copilot-accessible context such as conversation memory and user details (e.g., location and activity/history), with the staged prompting designed to appear benign while progressively leaking information to attacker-controlled infrastructure.
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