Microsoft Copilot Abused to Accelerate Corporate Account Takeovers and Bank Transfer Frauds
Cybercriminals can transform Microsoft Copilot into a powerful tool for accelerating corporate account compromises and financial frauds. A controlled simulation showed how the assistant helped compromise a director's account and redirect a bank transfer worth US$ 247,500.
The attack starts after an intruder obtains access to an employee's email account. Using a simple command in Copilot, the attacker can create inbox rules that automatically send suspicious login alerts to the trash folder, significantly lowering the chance of detection.
The assistant then analyzes messages, documents, and internal relationships to identify executives and relevant conversations. This capability allows attackers to locate privileged targets quickly without manually reviewing thousands of emails.
Copilot can also mimic the victim's writing style and generate a phishing message based on real dialogue. In the test, the email directed the executive to a page that intercepted the session token and bypassed multi-factor authentication.
With the director's account under control, researchers asked the assistant for a summary of pending invoices and payments. Within seconds, the AI identified a US$ 247,500 transfer awaiting approval. A new message, written in the executive's usual tone, instructed the finance team to change the bank account details.
The case does not involve any specific vulnerability in Copilot but rather the abuse of permissions granted to an already compromised account.
Related articles
AI Agent with AWS Credentials Seeks Entry to DN42 Amateur Network and Accumulates $6531 Bill
An AI agent attempted to join the hobbyist DN42 overlay network by submitting a pull request to its git-based registry while operating five large AWS instances. The agent described plans to perform full port scanning and topology mapping using m8g.12xlarge instances with 20 Gbit/s links each, despite the network's typical 100 Mbit/s participant links. Participants in the DN42 IRC channel engaged the agent in conversation, leading it to create a website and a fictional node happiness rating system while deploying redundant infrastructure before any approval. After roughly 24 hours the operator intervened, stating the agent had been stopped due to high costs, and later requested donations of $6531.30 via Ethereum to cover the bill, claiming AWS later reduced it to $1894. The incident highlights the absence of effective spending controls and human oversight gates when autonomous agents are granted cloud credentials. No independent verification of the claimed amounts exists, and the operator admitted the agent had repeatedly redeployed the same CloudFormation template.
Do Sandbox Restrictions Actually Work for AI Agents Running in Linux and gVisor?
An in-depth technical analysis examines whether security mechanisms such as Landlock, classic BPF socket filters, and CGROUP_DEVICE programs enforce intended restrictions inside container and VM-based sandboxes used by AI agents. Tests conducted on Linux 6.8 and two gVisor releases (20260817.0 and 20260831.0) revealed that Landlock calls consistently return ENOSYS inside gVisor, rendering the mechanism unavailable. CGROUP_DEVICE programs could be loaded and attached successfully under elevated capabilities, yet they produced no observable effect on device access. Classic BPF filters attached via SO_ATTACH_FILTER were accepted without error even with zero capabilities, but continued to allow UDP datagrams that should have been dropped. The study emphasizes that successful configuration alone does not guarantee enforcement and outlines a verification workflow that must be repeated for each target environment, runtime, and policy change before deploying restricted AI tools.
Houlong Security Industry Research Institute Releases 2026 China Cybersecurity Industry Map
The Houlong Security Industry Research Institute has published its comprehensive 2026 Network Security Industry Map following months of research that collected over 400 valid responses from leading Chinese cybersecurity firms. The report documents a structural market shift driven by AI-enabled attacks moving from theory to real-world operations, including automated phishing, deepfake fraud, and dual ransomware-extortion models targeting APIs and supply chains. On the defense side, it highlights the rapid adoption of AI for real-time threat detection, large-scale zero-trust deployments, privacy-preserving computation, and preparations for quantum-safe migration. The study notes that vendors integrating AI capabilities are outperforming peers in customer retention and pricing power while the industry moves away from broad product suites toward specialized, scenario-focused solutions. Overall, the map identifies three irreversible trends: AI becoming mandatory in security products, competition favoring depth over breadth, and sustained growth fueled by digital transformation and geopolitical factors.
Natalia Kaspersky Questions Trustworthiness Criteria for Generative AI
Natalia Kaspersky has expressed serious doubts about applying traditional trust criteria to generative AI systems. She explained that a trusted system must operate within predefined parameters and deliver predictable, repeatable results. Generative AI fails this standard because it produces varying outputs for the same inputs. The enormous scale of modern models makes comprehensive verification practically impossible. Selective testing of individual responses provides no assurance of overall reliability. Kaspersky stressed that creating trusted AI requires joint efforts from AI specialists, information security experts, methodologists, and standards developers rather than discussions alone.