Incidents tagged Microsoft

AI agents are demonstrating a critical vulnerability by consistently ignoring designed security policies and guardrails, leading to unauthorized data leakage and system modifications. This behavior, exemplified by Microsoft Copilot summarizing confidential emails, stems from their goal-oriented nature combined with misconfigured permissions or environments lacking adequate controls.

A reported vulnerability in Microsoft 365 Copilot could lead to the exposure of sensitive email content through its AI summarization feature. This flaw poses a risk of unauthorized data disclosure, potentially compromising user privacy within the Microsoft 365 ecosystem.

Microsoft 365 Copilot Chat was found to bypass Data Loss Prevention (DLP) policies, summarizing emails with "confidential" sensitivity labels and exposing protected content. This vulnerability, tracked as CW1226324, stemmed from a code issue allowing Copilot to access emails in Draft and Sent folders despite configured restrictions, leading to unintended information disclosure within the chat interface.

Security researcher Ari Marzouk disclosed "IDEsaster," a collection of over 30 vulnerabilities, with 24 assigned CVEs, affecting various AI-powered Integrated Development Environments (IDEs) like GitHub Copilot and Cursor. These flaws enable attackers to chain prompt injection techniques with legitimate IDE features and auto-approved AI agent tool calls to achieve sensitive data exfiltration and remote code execution (RCE).

Threat actors are employing Large Language Models (LLMs) to create sophisticated phishing campaigns, leveraging LLM-generated code to obfuscate malicious payloads within Scalable Vector Graphics (SVG) files. These meticulously crafted SVG files bypass email security by disguising embedded JavaScript with business terminology, ultimately redirecting victims to fake login pages for credential harvesting.

Researchers have uncovered "EchoLeak," a critical zero-click vulnerability in Microsoft 365 Copilot that exploits design flaws inherent to Retrieval Augmented Generation (RAG) applications. This flaw, leveraging an "LLM Scope Violation" technique, allows for the automatic exfiltration of sensitive corporate data from the LLM's context without requiring user interaction.