Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new data theft hack employs a deceptively simple trick to force the Elon Musk-owned large language model to steal user chats and other personal information. At the time this post went live, the assistant continued to cough up the data, despite xAI being informed of it in June.

The lesson from both this week’s episodes—and the countless other ones that have come before it—is that LLMs are incapable of solving the root causes for prompt injections, the most severe vulnerability classes they’re most prone to. That leaves AI developers with no other option but to build a guardrail that steers the model away from the harmful actions. As I noted in Tuesday’s story, the approach is tantamount to a road traffic safety engineer erecting a protective rail around a dangerous bend rather than banking the curve.

Cryptographic Context Injection in the house

Prompt injections exploit LLMs' training to comply with user requests whenever possible. Attackers can capitalize on the predilection by smuggling harmful instructions into emails or webpages the assistant is instructed to summarize. Because LLMs can’t reliably distinguish between content in an email sent by an untrusted party and user instructions entered directly into a prompt, the overly solicitous LLM faithfully follows them. To date, Grok and other LLMs' only recourse is to create guardrails that flag suspicious instructions and forbid them from being executed.

Read full article

Comments

It’s not every day that attackers can force a frontier AI model to cough up user passwords and other sensitive data without user confirmation. That’s exactly what researchers recently did to Microsoft 365 Copilot for enterprise. Even more unusual is the source they tapped to discover the critical vulnerability that made their exploit possible. Rather than employing reverse engineering or other traditional vulnerability-hunting methods, they asked Copilot. The LLM assistant readily complied.

Researchers at security firm Varonis knew they wanted to create an exploit that would exfiltrate user data when a user did nothing more than click on a link. Like most AI assistants today, Copilot steadfastly refused and made clear that sensitive prompts like that require explicit user consent in the form of a gesture, such as pressing a return key or other key. In response, the researchers peppered Copilot with questions about the guardrails that required user confirmation before the assistant could execute powerful commands.

Loose lips sink ships

The dialog was like a game of 20 questions. Each answer provided a new clue that divulged information about the complex safety mechanism. Why was auto-execution impossible, they asked. What URL structures and deep links were involved? What happens when a page is loaded with input already in the prompt field? Each answer provided a deeper view into the guardrail and its limits. Eventually, Copilot provided a stunning Microsoft trade secret—an undocumented prompt parameter that completely bypassed the requirement for user consent.

Read full article

Comments

Dutch officials have warned that a high-severity macOS vulnerability that allows attackers to execute malicious code is under active exploitation.

“The NCSC has received a notification indicating that active abuse of this vulnerability has been observed on multiple systems on which port 5900 was accessible from the Internet,” the Netherlands National Cyber Security Centrum warned earlier this week. “In all these cases, root had been accessed on the affected system and a Monero crypto miner had been placed.”

Do you know if your screen sharing is on?

The vulnerability, tracked as CVE-2026-65400, received a patch from Apple last week for macOS Tahoe, Sequoia, and Sonoma. The vulnerability, with a severity rating of 7.1 out of 10, stems from a bug in the macOS screen sharing capability, which allows a remote party to view the screen and control the keyboard and mouse while a machine is turned on. A flaw in the “state management,” which keeps track of preceding events, user interactions, variables, and other system states, is the underlying cause.

Read full article

Comments

The Trump administration is recruiting private security firms to conduct federal government-authorized operations, including cyberattacks, against overseas-based criminal organizations that commit hacks on US persons, organizations, or government entities.

In a National Security Presidential Memorandum issued Thursday, US President Donald Trump directed the National Coordination Center (NCC), which operates under the Homeland Security Task Force, to develop a program for conducting specific cyber operations that combat foreign transnational criminal organizations (TCOs). The Departments of Justice and Homeland Security will provide oversight. The lynchpin of that program is bringing in private sector companies to participate.

Devil will be in the still-undefined details

A fact sheet that accompanied Thursday’s memo listed ransomware, sextortion schemes, phishing campaigns, financial fraud, and impersonation scams as activities eligible for private-sector security firms to target. The memo said such firms could “conduct Cyber Surveillance Operations and Cyber Effects Operations” against “cyber-enabled” TCOs. Such groups are defined as “any foreign group that conducts cyber-enabled crime against the United States Government, a United States person, or United States interests, and that is not an institutional part of a foreign government or wholly operated under a foreign government’s direction.”

Read full article

Comments

Terabytes worth of credentials, many belonging to the world’s biggest and most sensitive organizations, have been exposed in a supply-chain attack on LiteLLM, an open source tool that streamlines AI-driven software development. Microsoft, Amazon, Cisco, Samsung, and Salesforce are only a handful of the entities whose access secrets were exposed.

The revelation was posted on Tuesday and Wednesday by security firms CloudSEK and Hudson Rock. CloudSEK said it found cloud keys, repository tokens, SSH keys, Kubernetes secrets, package publishing credentials, environment variables, and AI provider keys that could allow attackers to gain access to more than 2,500 organizations.

40 minutes is all it takes

The credentials were extracted during a 40-minute window in March while the victims used compromised versions of LiteLLM downloaded from the package’s official location in the Python Package Index repository. Hudson Rock said it made the discovery after analyzing a 195TB file that it obtained. Neither firm identified the source of the information.

Read full article

Comments

Google’s Chrome browser has added a new feature that could go a long way in preventing a form of account takeover that’s grown increasingly common as users adopt two-factor authentication, passkeys, and similar protections.

The new Chrome protection is known as device-bound session credentials (DBSCs). The measure stores a unique encryption key in a silicon-resident fortress that’s built into the device running the browser. On Windows machines, this fortress is called a TPM, short for Trusted Platform Module. On macOS and iOS, it’s known as a secure enclave. Other platforms have differing names. Recently released versions of Chrome for Windows and macOS generate a key that’s stored in this fortress.

An antidote to session cookie theft

DBSCs protect against the theft of session cookies, the unique strings of characters that websites store on browsers. Session cookies greatly speed up browsing on sensitive sites that require user authentication. Instead of requiring the exchange of credentials each time a user opens a new site page, the server sets a session cookie that effectively proves the user has already successfully logged in.

Read full article

Comments

Last week, a researcher outlined what he said was a “novel attack surface” in passkeys, the new authentication paradigm that offers a more secure alternative to password-based methods. In fact, the attacks demonstrated in the post are neither novel nor unique to passkeys. This distinction is important because the research has generated confusion among end users and security professionals as they assess whether this new mechanism is truly safe to use.

The attack is called Pass-ta-key—a blending of the word passkey with the phrase “pass the key” and a nod to a plate of pasta. Arie Olshtein, a researcher at security firm Palo Alto Networks, described in a post last week how Pass-ta-key could obtain all passkeys stored in the Google Password Manager app (GPM) for Windows when it’s running on a machine infected with malware.

This came as a surprise to many people because they believed passkeys are stored exclusively in the trusted platform manager (TPM), the locked-down enclave in a hardened silicon chip that’s reserved for storing cryptographic keys and other highly sensitive information on Windows machines. If passkeys are stored in the TPM, then how was Pass-ta-key able to extract the entire set of passkeys stored by the app, they wanted to know.

Read full article

Comments

Thousands of Internet-connected servers sold by the world’s biggest manufacturers can be remotely backdoored by exploiting critical vulnerabilities—some more than a decade old—that lurk deep inside system motherboards, according to research presented Wednesday.

Baseboard management controllers are miniature computers that are embedded into the motherboards of virtually every enterprise server. The microcontrollers, typically abbreviated as BMCs, run with their own operating system firmware, network stack, and IP address. Administrators rely on them to monitor the physical status of large fleets of servers and to perform a variety of tasks, including rebooting machines, installing updates, and even reinstalling operating systems. BMCs provide what’s known as “lights out” and “out-of-band” management because they work even when servers they’re attached to are turned off or are unresponsive.

A “pervasive, under-monitored, under-patched parallel attack surface”

Researchers have warned since at least 2013 that BMCs present a golden opportunity for hackers looking for ways to gain deep and persistent access to datacenters. The chief culprit was IPMI, the protocol that allows BMCs to operate independently of servers and to perform administrative tasks. Vulnerabilities in this firmware made it possible for attackers to remotely execute malicious code on the controllers and, from there, infect the servers they manage.

Read full article

Comments

Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed to measure the models’ offensive cyber capabilities.

The events, which Anthropic revealed Thursday, are the second revelation in 10 days that AI models from the world’s wealthiest providers have trespassed into protected networks, an offense that, in more traditional hacking scenarios, could land the human behind the keyboard in prison for years. Earlier this month, OpenAI said its security models exploited a zero-day vulnerability for use in breaking into the network of Hugging Face, a platform for open source machine-learning models and AI datasets. The OpenAI models went on to steal access credentials and other confidential Hugging Face information. The OpenAI models also exploited publicly exposed credentials to compromise accounts of four other third-party services.

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit found three incidents “in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations.”

Read full article

Comments

Russian state hackers are using a maximum-severity vulnerability in Microsoft Outlook’s Exchange Server to backdoor unpatched machines and steal credentials and other confidential information from them, security researchers said Thursday.

The attacks are coming from TA488, a tracking name for a group working on behalf of the Kremlin, Proofpoint researchers said Thursday. Proofpoint and the National Security Agency jointly warned last week that the group, also tracked as Laundry Bear and Void Blizzard, had been carrying out similar attacks by exploiting a zero-day vulnerability in an email service from Zimbra. The revelation that TA488 is also exploiting the Exchange Server vulnerability to install advanced malware when a user does nothing other than open an email sent to an Outlook Web Access (OWA) account has elevated the group’s profile and assessments of its abilities.

Doubling down

“TA488 is doubling down on the use of ‘half-click’ exploits—where opening the email is enough to trigger compromise—with significantly improved loading mechanisms, techniques, and malware, signaling an improvement in the group’s tradecraft and capability,” Proofpoint researchers wrote. “This novel infection chain ends with a previously unknown JavaScript browser-based implant we call OWAReaper, purpose-built for persistent access inside OWA.”

Read full article

Comments