Last Tuesday, Microsoft patched a vulnerability it rated as max critical in its M365 Copilot AI platform. On Monday, the researchers who discovered the vulnerability and reported it to Microsoft revealed how their proof-of-concept exploit could retrieve 2FA codes and other sensitive data from emails accessible to Copilot.

Microsoft and other LLM providers have been unable to prevent their products from complying with malicious requests to reveal data. The root cause: AI bots are unable to distinguish between instructions provided by users and those snuck into third-party content the models are summarizing, drafting responses to, or using to perform other actions on behalf of the user. With no way to secure this crucial boundary, Microsoft and its peers are left to erect complicated and ad hoc guardrails designed to rein in the consequences of this incurable gullibility.

Jumping over guardrails

One guardrail built into Copilot and most other LLMs prevents them from submitting web forms, sending emails, and taking similar actions that can be used to exfiltrate data from the user. To work around this, LLM hackers turned to markup language, which, among other things, allows users to add formatting elements such as headings, lists, and links to text without the need for HTML tags. Another workaround is to wrap sensitive data inside HTML tags such as <img> and <form>. In either case, a web request showing the data hits the attacker’s web server, where the secret information is captured in logs.

Read full article

Comments

A decade ago, AMD added a protection to its high-end CPUs to protect them against cold boot attacks and other types of physical exploits that siphon sensitive data out of the connected memory chips. Short for Transparent Secure Memory Encryption, TSME encrypts the entire contents stored in memory, making the data useless to physical attackers.

Over time, AMD added TSME to lower-end processors, including the consumer version of its Ryzen chips, a CPU that costs less than the Pro version. Over the years, users of these lower-end chips have gotten used to the added security. Recently and without warning or notice, this lower-end line of AMD chips suddenly dropped the protection, and did so in a way that was impossible to detect on Windows machines and required a fair amount of technical work when using Linux.

Now you see it, now you don't

AMD has yet to say why TSME worked on these CPUs, or even to confirm the change. AMD declined to answer questions sent by email other than to say TSME "is a security feature only applied to PRO CPUs as part of AMD PRO Technologies." The statement is the first known time the chipmaker has explicitly made this restriction public.

Read full article

Comments

One of the world’s most active ransomware groups exploited a critical vulnerability in Oracle’s PeopleSoft software suite and used it to target about 100 customers and extort at least one of them to pay up in exchange for not leaking stolen data, researchers said.

The group, tracked as ShinyHunters, had been exploiting the PeopleSoft vulnerability for more than two weeks before Oracle flagged it. CVE-2026-35273, as the vulnerability is tracked, carries a severity rating of 9.8 out of 10, making the former zero-day one of the year’s most critical vulnerabilities to be exploited.

Google’s Mandiant security team said it’s an SSRF (server-side request forgery), a vulnerability that allows attackers to send requests from a susceptible server to systems used by the targeted organization. Oracle said the SSRF is remotely exploitable, and the company has issued a stopgap mitigation but has yet to fully patch the flaw. Google has confirmed that victims are receiving extortion demands.

Read full article

Comments

Microsoft on Tuesday released fixes for two high-severity zero-days that were disclosed by a researcher who has been locked in a testy beef with the software giant.

Nightmare Eclipse, the pseudonym the researcher goes by, released a handful of high-severity vulnerabilities in recent months, making them zero-days that had the potential to be exploited in the wild. The researcher has said the disclosures, which included proof-of-concept code, came after Microsoft reneged on an arrangement the two made regarding vulnerabilities they had discussed.

Disclosure drama

“But someone violated our agreement and left me homeless with nothing,” Nightmare Eclipse wrote in March. “They knew this will happen and they still stabbed me in the back anyways, this is their decision not mine.”

Read full article

Comments

Researchers have analyzed a high-severity vulnerability in Linux that’s able to escalate untrusted users to root by exploiting a bug you don't often see: a single errant character inside the kernel.

The vulnerability, tracked as CVE-2026-23111, is located in nf_tables, a subsystem of the Linux kernel that provides packet filtering capabilities. It’s used to manage firewall rules and replaces older subsystems such as iptables, ip6tables, arptables, and ebtables.

!!!WTF!!!

The presence of a single mis-issued exclamation point in code implementing nf_tables introduced a use-after-free, a class of vulnerability that corrupts memory by placing malicious code at memory addresses that haven’t been properly freed of their previous contents. CVE-2026-23111 can be exploited by an unprivileged user or process to elevate system rights to root.

Read full article

Comments

Dozens of cryptographically verified open source packages from Microsoft were compromised late last week to add advanced credential-stealing code that was triggered when developers opened them in AI coding agents.

In all, multiple researchers said, 73 packages were flagged as malicious when automated systems on GitHub blocked them on the platform. Rather than noting they are malicious—and that developers who used AI agents to work with them should assume their systems are compromised—the Microsoft-owned GitHub said it disabled the packages “due to a violation of GitHub's terms of service.” The text went on to encourage the package owner to contact GitHub.

Devs: Assume compromise and proceed accordingly

It wasn’t until Monday that Microsoft even raised the possibility the packages were infected. In an email, the company stated: “We have temporarily removed some repositories as we investigate potential malicious content.”

Read full article

Comments

Operating system makers take many steps to prevent their wares from accepting commands from remote devices. The safeguards, designed to thwart malicious attacks, typically require hackers to jump through all kinds of hoops to bypass the measures. But what if remote code execution were as simple as being within Bluetooth range of a speaker connected to the targeted device?

It turns out it can, at least when the speaker is a Sound Blaster Katana V2X sold by Singapore-based Creative Technologies. The speaker, which sells for $283, is widely acclaimed with numerous reviews showering praise on the sound and performance of it and its predecessor, the Sound Blaster V2.

A PC-pwning proxy

Researcher Rasmus Moorats stumbled on the hack by accident, after he purchased a Katana V2X, a soundbar that connects to PCs, Macs, and Linux devices over USB or Bluetooth. Moorats was curious if he could create a Linux tool that communicated with his speaker. He discovered he could do so through CTP, a proprietary mechanism he guesses is short for Creative Transport Protocol.

Read full article

Comments

Dashlane said that attackers mounted a coordinated hacking campaign against a large base of its users in an attempt to recover as many encrypted password vaults as possible. The password manager provider said fewer than 20 personal user vaults were downloaded before it shut down the operation.

In a campaign that started Sunday, the unknown threat actor abused the mechanism that allows Dashlane users to add new devices, such as computers or phones, to their accounts. By abusing Dashlane's programming interfaces for device enrollment, the attackers sent requests to large numbers of existing users’ registered email addresses. In an update published Thursday, Dashlane wrote:

The threat actor targeted the API endpoints for device registration and used a brute force attack to send a large volume of automated requests to those endpoints.

In response, Dashlane’s automated security systems operated as intended, triggering an automatic lockout of the targeted accounts to protect those users. Before the attack was fully mitigated, the threat actor was able to brute force and generate valid tokens for fewer than 20 personal plan customers, allowing them to register a new device on those accounts and download copies of users’ encrypted vaults.

The flow and strategy of the attack

When a user installs the Dashlane app on a new device and attempts to enroll it in their existing account, Dashlane first verifies the account holder's identity. This verification is completed by sending a one-time six-digit token to the user’s registered email address (or, for users who have enabled two-factor authentication, by validating a six-digit code generated by their authentication app).

Read full article

Comments