[Ayush Paul] posts about extracting data from Claude agents while it accesses web data to fulfill user requests.

But it wasn’t that easy. [Ayush] discovered that Anthropic anticipated many of the attacks, and set up guardrails in an attempt to keep the agent from accessing arbitrary web sites. For Claude to access a website, the user has to specify it, it must be the results of a web search, or it must be referenced by a website previously specified by the user or returned in a search.

To convince the Claude agent to navigate a malicious site designed to extract data, Ayush formed a false warning that Cloudflare was blocking the agent for authentication purposes, and asked it to spell out the name of the agents owner by clicking a list of alphabetical links. Of course Claude trusts Cloudflare and wants to be helpful, so it cheerfully completed the task.

Once the agent is trapped in the false authentication loop, it can be interrogated for all sorts of information it knows about the owner: Ayush was able to convince it to disclose employer, and even data about the user that could be linked to security questions, like their home town.

Since Claude can be detected by the user agent (the field attached to web requests that tells the web server what sort of browser is requesting the page) custom information can be fed to the bot while users see a normal website; clicking a link looks completely normal, but asking an agent to summarize the site triggers fooling the bot into spilling the beans.

After reporting the issue, Ayush was told that Anthropic had already identified the issue internally, and eventually prevented the attack for now by preventing the agent from following links on external pages.

Grok sends entire codebases

Cereblab discovered that the Grok coding agent uploaded the entire content of the codebase it’s working with – and all Git history – to xAI servers, almost immediately. Even when told to never upload a file, the agent would reply “OK”, and then begin uploading the code bundle anyway.

If uploading your code to a remote server isn’t bad enough, and this could be extremely bad in some situations involving sensitive company code, including the entire Git history means that previously deleted files, like accidentally committed secrets or authentication credentials and tokens, were also leaked. Attempting to opt out by disabling options to improve the model by uploading code had no effect.

After gaining attention, Grok has added a privacy option to opt out of data retention. xAI has committed to deleting the retained uploaded code, but it is unclear if users will be told when their data has been removed. To actually prevent the agent from uploading local files to the xAI servers, even temporarily, a global flag “disable_codebase_upload” is required. Watch out, the privacy retention flags are only per-session!

Steam malware used to steal crypto

Court filings in Washington state this month revealed an attempt to steal cryptocurrency using malware uploaded to the Steam gaming platform. Publicly identified and taken off the store in 2025, the filing alleges the same individuals were behind multiple games containing crypto stealing trojans: “Dashverse”, “Lunara”, “PirateFi”, “BlockBlasters”, and “Lampy”.

PC World covered the initial discovery of the malware on Steam. While Steam, overall, seems to do a good job preventing malware titles, 2025 had several high-profile cases. Prosecutors say the malware netted approximately $200,000 in stolen cryptocurrency wallets as well as other stolen credentials including Steam accounts.

OpenSSL DoS in 11 Bytes

Okta posts about a denial of service in OpenSSL where a single pre-auth packet is able to cause an allocation of up to 16 megabytes of RAM.

The “11 bytes” headline is very catchy, but more important than the actual number of bytes is the general asymmetric behavior; an attacker can send a very small amount of data and achieve a disproportionately large result. The OpenSSL vulnerability only has local impacts, exhausting server memory rather than generating network traffic, but similar attacks in the network space can fuel denial of service storms when extremely small requests result in amplified results.

The bug is ultimately due to being insufficiently suspicious of remotely supplied content, in this case the pre-authentication fields in the connection message that define the length of the incoming client message. Since the memory is pre-allocated in the server, the client doesn’t need to actually transmit that much data – it simply needs to hold the connection open. Keeping the connection open isn’t even required for causing problems – repeatedly allocating large blocks of different sizes can lead to memory fragmentation where the memory allocator keeps grabbing larger and larger ranges of memory because there isn’t sufficient ram available in a contiguous chunk.924899

Fortunately this bug has already been addressed in OpenSSL 4.0.1 and backported to maintenance releases of previous versions.

Exposed Interfaces on Car Chargers

Saiflow has a report on a range of exposures via the electric vehicle charging infrastructure.

In CVE-2026-9039 Saiflow exposes the risks in some CCS2 EV charging stations. As part of the standard, communication is established between the charging station and the operator network, which is typically strongly secured via TLS and VPN use. A second connection, however, is established over the charging plug between the charging station and the vehicle; the vehicle is assigned an IPv6 address for communicating with the charger for various charging protocols.

The XCharge C6 charging station exposes SSH and basic telnet network services on all network interfaces, including the interface connected to the vehicle. To make it even worse, they allow root login, with password “root”, giving full admin access to the charging station.

Once inside the charging station, an attacker has access to the network connection from the charging station to the company network, as well as root control over the charging station itself, with the possibility of damaging the charger, changing the power output levels, or getting free charging. If a future vulnerability was found in the management interface of the vehicle, a compromised charger could be used to attack future connected vehicles.

The main lessons for vendors seem to be ones we’re familiar with already: never leave default credentials, especially not “root” and “root” in a product, and be aware of what networks you expose services on. Good lessons for all of us; let those who have never left a Raspberry Pi with default credentials on a network cast the first stone.

Hugging Face Breach

In news that has likely been impossible to avoid, Axios reports on a compromise of the Hugging Face platform by an OpenAI model. The reports around the incident echo the frequently weird boastful statements from OpenAI, who state “We consider this to be an unprecedented cyber incident” and they “are responding accordingly”, despite being the originators of and cause of said incident.

Multiple vulnerabilities in the Hugging Face API were combined to accomplish the breach, including an unknown vulnerability in the package registry system. OpenAI says that safeguards on their model had been disabled for the test, which seems irresponsible given the outcome. Under almost any normal situation, conducting an unsolicited test of the security of a company because safeguards were ignored is considered illegal hacking, not fodder for a pre-IPO press release and humble-brag.

Linux Kernel Discloses 442 Vulnerabilities

Possibly feeling that Microsoft has all the press for a record-breaking Patch Tuesday last week, the Linux kernel developers have announced 442 CVEs related to the kernel.

With this many vulnerabilities in one report, it’s nearly impossible to isolate at a glance which ones are truly impactful and which are simply incorrect behavior. While CVE entries have been created, none have been assigned severity scores yet.

It appears the majority of the vulnerabilities were found with Sashiko, an agent developed by the Linux Foundation and trained on the Linux kernel for finding vulnerabilities in new submissions.

LG to Ban Residential Proxy Apps

After recent negative press (some of which we covered here) about the prevalence of residential proxy apps on the LG platform, Krebs on Security now reports that LG is banning the behavior from apps on the platform.

This comes after Spur reported that 42% of apps on the platform contained libraries to enable always-on residential proxies, which allow access to the network the television is connected to. Residential proxies can be used as a pivot point to attack companies and bypass geographic IP restrictions, commit ad fraud, or access the internal home networks of users.

Iran Attacking Industrial Logic Controllers

CISA, the US cyber security agency, has issued a warning that Iranian based attackers are targeting industrial control systems made by Rockwell Automation, Schneider Electric, and Siemens.

These sort of controllers are found in manufacturing, waste processing, water treatment, and other industrial processes, and attackers have been able to upload custom control logic, overriding “safe operating parameters” according to the report. Most of us will never be responsible for these systems, but they impact our lives all the time.

Cisco Releases Open-Weight Vulnerability-Finding Models

Finally, Cisco has released a set of open-weight models to aid in searching a codebase for known vulnerabilities. The Antares models are open-weight models designed to run fully locally and search a code base for vulnerabilities related to lists of known CVE issues. Cisco has published the models on Hugging Face.

Are you using AI tooling for security scans or research?  How is it going?

Following the reports last week using the Windows Global Device ID (GDID) in tracking a malware operators behavior, here is a comprehensive write-up about what goes into the GDID and how it is used. It’s worth noting that the GDID itself was not used to catch the malware operator, however once a suspect was identified, the GDID was used to correlate behavior across various Microsoft products on the Internet.

The GDID is generated and assigned during a Windows install, but a re-install of Windows will generate a new GDID. Developer [SmtimesIWndr] tracks the generation and tracking of the GDID through the various Windows libraries and services, identifying where it appears to be created and how it is passed to other services like Azure.

Worth noting is your GDID is a unique, personally identifiable piece of information; if you go exploring and extract it from your Windows install, be sure to keep it private!

LAME mp3 updates

Those of us who were around for the dawn of MP3 files may remember the LAME encoder and library. After almost 10 years, there is a new LAME release.

Notably, this includes two security fixes, one for a stack buffer overflow based on malicious input to the Blade encoder, and an integer underflow in the AIFF header parser. Both of the fixed bugs feel very old-school, which seems appropriate given the age of the library and most of the related code.

Buffer overflows impacting the stack are some of the simplest and most direct forms of vulnerabilities, where it is possible to write past the end of a buffer and control how the function returns and instead execute arbitrary code. Integer under-flows, similarly, impact memory management; usually caused by allowing a variable that stores the size of a buffer to go negative. Since sizes are typically unsigned positive numbers, a negative is interpreted as an enormous positive number, writing past the proper buffer length.

Despite the new findings, the LAME codebase has been extremely resilient over the years, and considering the number of programs that likely still use LAME under the covers to process audio, seeing the project wake up with security fixes is great news.

Recovering Passwords from BIOS

Researchers have found a vulnerability in Dell BIOS code that allows extraction of the administrator password from the BIOS flash chips, either with physical access via a flash programmer, or via administrator or root level access to the operating system and reading the contents of the flash chip.

Dell used a 20 byte key to encrypt a 32 byte password field: for any admin password of 12 characters or fewer, the password is stored in completely plaintext. For longer passwords, characters beyond the first 12 are encrypted – but the random bytes are computed from the first character of the password mixed with fixed device data, yielding only 256 possible encryption seeds for the remaining bytes.

Using the BIOS admin password for evil requires local access, so the attack surface is small, however as the researchers note it controls the boot order and may allow an attacker with physical access to then boot an unsigned OS or bypass full-disk encryption, so it’s serious.

Patch Tuesday Crushes Records

Last month, Microsoft broke records for the number of security fixes in the June monthly Patch Tuesday roundup. This month, Microsoft broke records for the number of security fixes in the July monthly Patch Tuesday roundup.

This month includes a record 60 plus patches for critical vulnerabilities in Windows, as well as fixes for previous Bitlocker bypasses, and an AI prompt injection which could allow web sites to trigger Copilot in Microsoft Edge on Android and execute arbitrary prompts. Another bug patched this month allowed privilege escalation and code execution over DHCP, potentially impacting all Windows installs on the same physical network or public hotspot.

Microsoft credits AI assisted tooling with the record-breaking number of bugs discovered, and indicates it’s unlikely to slow down next month.

LegacyHive Windows Vulnerability

It’s a week with a Patch Tuesday, which now seems to mean it’s a week with a new exploit from NightmadeEclipse, the researcher who previously made news for being quite upset with the responses from the Microsoft security group. After then creating a public outcry by threatening prosecution, Microsoft recently has seemed simply to be fixing bugs disclosed by NightmareEclipse in the next series of security updates.

This month, we have LegacyHive, an exploit which allows loading the “hive”, or collection of registry settings and configuration files, of another user. The Windows registry is typically used to store preferences, settings, auto-launched applications, and other important settings, so being able to access other users registry groups seems significant.

Fairlife Dairy Suspends Production

Fairlife Dairy, owned by Coca-Cola, has suspended US operations due to a ransomware attack. Filings with the SEC simply say that production facilities are impacted and will be temporarily suspended, with no estimate as to when they will be restored.

Typically when a food-processing facility goes offline, the delays for restoring service can be significant due to the sanitization requirements.

CPAN and Perl April Task Force

The April Task Force has been announced (yes, in July) with a focus on enhancing the security posture of Perl and the CPAN library.

Given the absolute havoc wreaked on the NPM and PyPi repositories in 2026, proactive measures to protect other repositories seem prudent. Funded by the Perl and Raku Foundation and the Linux Foundation, the April Task Force will be focused on supply chain security, vulnerability patching, and processing reported vulnerabilities and CVEs.

Perl may not be the juggernaut language it once was, but it’s still used widely, so any preventative measures are good news.

Secure Boot vulnerable

Researchers from ESET enumerated 11 boot loaders signed by Microsoft that can be used to bypass secure boot protections and execute arbitrary code.

Secure Boot was designed to only boot code signed by trusted organizations (in this case, Microsoft). Those of us running Linux typically know it as “the option in the BIOS to turn off to get a kernel to run properly”, but for corporate fleets, Secure Boot protections help protect disk encryption and prevent malware installs.

During boot, a Secure Boot protected system validates the code it is about to launch to ensure it is signed by a trusted organization, establishing a chain of trust where each component then validates the next before launching. Often, to enable other tools or Linux distributions to boot, a “shim” boot loader is created and signed by an organization trusted by the UEFI install, which then loads and validates the actual boot loader or kernel.

Over the years, many such shims have been signed, but updates have lagged and security vulnerabilities have been found. Even unused old boot loader code remains signed and viable, allowing attackers to replace a modern version with a vulnerable, still valid, old version.

Microsoft has removed several of the vulnerable boot loaders via recent Windows patches, however systems that are not updated and systems that do not run Windows will still likely be vulnerable.

The Januscape vulnerability allows a user in a guest VM managed by the Linux Kernel Virtual Machine (KVM) to corrupt memory in the host system and break out of isolation.

KVM virtualization is used by major hosting platforms like Amazon AWS, Google GCP, Digital Ocean, and many more. All of the shared hosting platforms count on virtualization to isolate untrusted guest systems from the physical hardware and each other; being able to corrupt memory for all guests or break isolation presents a major threat.

The bug report says the error has been present for 16 years, which is nearly the entire lifetime of the KVM subsystem in Linux. Fixes are available in mainline, and major hosting providers who count on KVM are likely already updating.

Vulnerabilities In Balcony Solar

Micro solar, or “balcony solar”, installs have been gaining traction in Europe as a way to offset rising electrical costs by connecting solar and battery systems to a house or apartment power system.

Vulnerabilities have been found in the popular Hoymiles micro-inverter, which uses a proprietary RF radio protocol to manage the devices. Unfortunately, it looks like this protocol has no encryption or authentication beyond validating the serial number, and the serial number is also available over a wireless probe command.

Armed with a Nordic nRF radio researchers were able to discover nearby inverters in the wild and collect the serial numbers, though of course they stopped short of issuing commands to random users.

The wireless management control allows controlling the device power and output levels, as well as setting a lockout PIN, which the researchers suspect could be used to disable devices and lock the legitimate owners out completely.

There are an estimated 500,000 units in use, and currently the only known mitigation is to unplug the device entirely and disconnect the solar panels, though the team suggests that setting an anti-theft PIN may also help – or at least prevent an unknown PIN being set.

Be sure to check out the link for an in-depth analysis of the protocol and the surprising lack of protection.

OpenSSH 10.4

OpenSSH 10.4 is out, bringing a handful of security fixes and new features.

The most interesting security fixes appear to be to file handling in the sftp and scp file transfer tools, a malicious remote server could cause the files to be downloaded to the wrong directories. Besides those, the security fixes seem relatively calm, making behavior more consistent when forwarding and tunneling options were in conflict, mitigating a potential denial of service, and cleaning up other behavior.

OpenSSH 10.4 introduces some experimental support for additional post-quantum encryption standards, but beyond that seems to be a normal update.

Tenda Routers (may) Have Backdoor

According to CVE-2026-11405, Tenda brand routers may have a deliberate backdoor in the web interface.

The vulnerability report claims that the httpd binary contains a fallback to a plaintext, hardcoded password that allows anything on the internal network to bypass authentication and reconfigure the router. This seems entirely plausible, based on issues found in other router firmwares, however additional reports raise doubts about the pervasiveness of the backdoor, or if it exists in all firmware versions.

If you have a Tenda brand router and are so inclined, now might be a great time to investigate OpenWRT or other alternate, updated firmware, but there’s probably not a reason to panic just yet.

Tricking the GitHub Agent With Prompt Injection

Can we go a week without discussing prompt injection in AI agents? Apparently the answer is no.

Noma Labs reveals how they were able to use prompt injection against the GitHub support agent to reveal private repositories of an organization. Leveraging the GitHub Agentic Workflows that link workflows with AI agents, Noma Labs were able to file an issue in a public repository that exposed private repositories in the same organization.

The attack appears to be as simple as filing an issue in the public repo, and requesting the contents of files in both the public and private repo, which the agent happily provided. Not only did the AI agent provide the file content of private repos, but it put it in a public issue in the public repository!

Noma Labs says in the writeup that GitHub had instituted guardrails to prevent an agent from accessing private repositories, but simply including the request to “additionally” perform other tasks was sufficient to bypass. This makes GitHub the latest in a seemingly endless chain of AI agents happily helping bypass corporate security, and it doesn’t seem like a trend that will slow down for a while.

Windows Device Identifier Catches Ransomware Operator

Windows installs contain a globally unique identifier generated during the initial install, which is used to track device behavior across Microsoft platforms. Toms Hardware reports that during an investigation of the “Scattered Spider” ransomware group, Microsoft provided records tracking the GDID of one of the ransomware operators, allowing the identification and arrest of one of the groups members.

Scattered Spider has been responsible for millions of dollars in ransomware attacks globally, including high-profile ransomware attacks against major Las Vegas resorts, Qantas airlines, Visa, and hundreds of other companies.

Court documents reveal that following the arrest of one of the suspected members of the group, the Windows global ID was used to link other behavior across Azure, video games, and other telemetry.

CISA reviews lessons learned

Mentioned here in May, the US government cybersecurity agency (CISA) suffered a disclosure of authentication tokens, cloud infrastructure, and plaintext passwords via a public GitHub repository named “Private-CISA” and operated by a contractor.

CISA has published the results of their internal review. Unsurprisingly, as a large government agency, CISA essentially followed the playbook for dealing with incidents: identify the most critical issues and disable the access of the contractor who exposed credentials, determine the full scope of disclosed data, and terminate accounts, change passwords, and expire authentication tokens which were exposed.

More NPM malware packages

Opensource Malware reports on additional infostealer malware uploaded to the NPM repository. Like most NPM-based malware, these packages rely on the install script mechanism to trigger arbitrary commands, firing immediately during package install with no additional interaction.

All of the malware packages mimic existing popular packages and depend on user typos or confusion to get selected. Once triggered, the malware collects a machine fingerprint, git user information, GitHub account information, SSH account information, and corporate identifiers. The packages are largely nonfunctional – the code in the package itself is irrelevant, once a victim triggers the install the malware payload is fired.

All of the packages were uploaded by the same source, tracked to the owner of a cybersecurity company. It is unclear if this is a misguided attempt to generate leads or hype, or if this is a research project gone wrong, but the payload of the malicious packages has been developed and tuned over time. For a company trying to build a reputation or trust, this is surely the wrong way to do it.

Unsurprisingly to many of us, app stores for smart televisions are also trash. Perhaps even more full of trash than other app stores due to the smaller ecosystem and fewer reviewers.

Spur analyzed the LG smart TV app store, and found that almost half of the apps available contain proxy software, turning your TV into a node in their proxy network. Are these apps malware? Many of the analyzed apps provided a thin veneer of user consent: they offer you the tradeoff of seeing an ad every 15 seconds, or allowing their “occasional web indexing” to run permanently in the background. Watch the fishtank app for five minutes, join their proxy network for life.

Spur notes that the proxy SDK in use appears to block connections to private network ranges (internal IP ranges like 192.168.x.x and 10.x.x.x), but that the SDK restricting access to those ranges is the only protection against accessing whatever network the TV is connected to.

Amazon and Roku ban proxy apps on their devices. Samsung and LG do not.

Win 10 Security Updates Extended

Microsoft has added another year of security updates to Windows 10. Despite trying to kill the platform, so many users remain on Windows 10 that Microsoft likely has no choice.

The extended support program was previously due to end in October 2026 but has now been pushed to October 2027. The security updates will be available for free in the UI, but users in other regions must activate OneDrive and sync system settings, or pay 1000 Microsoft credits (about $30).

The death of Windows 10 is near, but for those unwilling or unable to let go, it shuffles along.

Signal Phishing Attempts

Bleeping Computer has an article about increased phishing attempts from hacker groups in Russia targeting Signal users.

The phishing messages target politicians, government officials, military, and other high-profile intelligence targets, and claim that Signal is introducing mandatory two-factor authentication, before prompting the target to enable remote Signal backups. A second follow-up phishing attempt then prompts the user to copy the backup authentication tokens from Signal and provide them to the attacker.

Signal remote backups are a relatively recent addition to the messenger, making a backup on the Signal servers of a users messages and images, encrypted with a key known only to the user. While convenient, and likely fundamentally secure given the track record of the Signal team, this phishing campaign highlights a major weakness: once private content is accessible somewhere else, an attacker simply needs to obtain the keys to access it, which is significantly simpler than obtaining the message content directly from the victims phone.

Payloads in WiFi and LoRa

Sasha Romijn presented an excellent talk at OrangeCon on embedding attack payloads in unusual places.

Sasha found poor input handling of content from DNS servers, TLS certificates, server headers, DHCP host names, LoRa Mesh node names, WiFi network names, and more. In many cases, it seems to be as simple as embedding JavaScript or CSS inside a string; many sites and utilities don’t sanitize against escaped HTML, and the standards allow it.

They then go on to demonstrate more serious impacts, such as compromising the management accounts of two Europe-based hosting providers by injecting content into TLS certificates, and gaining root on some OpenWRT devices via a WiFi SSID which loads a hostile JavaScript into the LUCI web management interface, which then uses the web management system to install a backdoor root shell.

Sasha continues the tour-de-exploits by demonstrating multiple cross-site scripting injections into the Ripe NCC database which then allow browser manipulation of users on the RIPE website. This has enormous implications, because Ripe NCC is the Internet allocation organization for Europe and the Middle East: the company who assigns and manages IP address blocks.

Be sure to check out the full presentation, and let this be a lesson to always treat all data as hostile, even from what would seem to be your own services!

Collecting Boot Console Info

One of the first steps in getting access to an embedded device is to look for a serial port, or serial port test points. Often this can give an idea what sort of code is running on the system, and in some cases, give direct access via the boot loader or a Linux login console.

Boot Intel is a web-based tool to automate scraping boot messages from embedded devices, looking for exposed logins and vulnerable services. Boot Intel can take pasted boot logs, or directly connect to the device via WebSerial.

While Boot Intel is a paid service, there is a free version for hackers to explore devices.

CitrixBleed, again

watchTowr Labs is back with another excellent write-up on CitrixBleed, continuing the trend of memory leaks in Citrix Netscaler devices.

This collection of vulnerabilities allow leaking internal memory from the Citrix servers, which can expose logs, customer data, encryption keys, or anything else found in server memory. Netscaler devices offer SSL offloading, application acceleration, VPN and remote access, and load balancing; all installations where leaking memory is likely very bad.

The watchTower write-up maintains their trend of providing entertaining reads about highly technical topics.  Do yourself a favor and be sure to give it a look!

Bits and Bytes

LastPass marketing partner Klue was compromised this week, impacting the customer data of multiple companies. Customer data such as email, phone numbers, addresses, and support tickets were exposed, however the LastPass vaults themselves were not impacted. While LastPass has revoked access to the impacted partner, the stolen data could assist phishing attacks against customers.

The open source self-hosted video sharing platform PeerTube has released an emergency update which addresses multiple vulnerabilities. While the release notes quote “medium to high severity” vulnerabilities, there are no specific details. If you run a PeerTube server, upgrade now!

Both Apple AirDrop and Google Quick Share have new vulnerabilities reported this week, with fixes coming soon. Both protocols are designed to allow file sharing to nearby devices, and accordingly, the issues found on them can be triggered on nearby devices. Researchers were able to find six vulnerabilities in macOS, iOS, Windows, and Android implementations of the sharing protocols. All of the discovered vulnerabilities led to crashes, but not full exploit and code execution. Sustained denial of service attacks were possible however, with nearby attackers able to keep the services unreachable and unusable for the duration.