This week on the Lock and Code podcast, we speak with Becky Holmes about how she tricks, angers, and jabs at romance scammers online.

_This week on the Lock and Code podcast…_

There’s a unique counter response to romance scammers.

Her name is Becky Holmes.

Holmes, an expert and author on romance scams, has spent years responding to nearly every romance scammer who lands a message in her inbox. She told one scammer pretending to be Brad Pitt that she needed immediate help hiding the body of one of her murder victims. She made one romance scammer laugh at her immediate willingness to take an international flight to see him. She has told scammers she lives at addresses with lewd street names, she has sent pictures of apples—the produce—to scammers requesting Apple gift cards, and she’s even tricked a scammer impersonating Mark Wahlberg that she might be experimenting with cannibalism.

Though Holmes routinely gets a laugh online, she’s also coordinated with law enforcement to get several romance scammers shut down. And every effort counts, as romance scams are still a dangerous threat to everyday people.

Rather than tricking a person into donating to a bogus charity, or fooling someone into entering their username and password on a fake website, romance scammers ensnare their targets through prolonged campaigns of affection.

They reach out on social media platforms like Facebook, LinkedIn, X, or Instagram and they bear a simple message: They love you. They know you’re a stranger, but they sense a connection, and after all, they just want to talk.

A romance scammer’s advances can be appealing for two reasons. One, some romance scammers target divorcees and widows, making their romantic gestures welcome and comforting. Two, some romance scammers dress up their messages with the allure of celebrity by impersonating famous actors and musicians like Tom Cruise, Brad Pitt, and Keanu Reeves.

These scams are effective, too, to sometimes devastating consequences. According to recent research from Malwarebytes, 10% of the public have been the victims of romance scams, and a small portion of romance scam victims have lost $10,000 or more.

Today, on the Lock and Code podcast with host David Ruiz, we speak with Holmes about her experiences online with romance scammers, whether AI is changing online fraud, and why the rules for protection and scam identification have changed in an increasingly advanced, technological world.

>  ”I’ve seen videos of scammers actually making these real life video manipulation calls where you’ve got some guy sitting one side of the world pretending to be somewhere else completely, and he’s talking into his phone and it’s coming out on the other person’s phone as a different image with a different voice.”

Tune in today to listen to the full conversation.

**Listen up—Malwarebytes doesn’t just talk cybersecurity, we provide it.**

Protect yourself from online attacks that threaten your identity, your files, your system, and your financial well-being with our exclusive offer for Malwarebytes Premium for Lock and Code listeners.

 Corpse-eating selfies, and other ways to trick scammers (Lock and Code S06E14) 

Malicious websites designed to rank high in Google search results for ChatGPT and Luma AI deliver the Lumma and Vidar infostealers and other malware.

AI-Themed SEO Poisoning Attacks Spread Info, Crypto Stealers

Palo Alto, California, 30th June 2025, CyberNewsWire

**Palo Alto, California, June 30th, 2025, CyberNewsWire**

Every security practitioner knows that employees are the weakest link in an organization, but this is no longer the case. SquareX’s research reveals that Browser AI Agents are more likely to fall prey to cyberattacks than employees, making them the new weakest link that enterprise security teams need to look out for. 

Browser AI Agents are software applications that act on behalf of users to access and interact with web content. Users can instruct these agents to automate browser-based tasks such as flight bookings, scheduling meetings, sending emails, and even simple research tasks. The productivity gains that Browser AI Agents provide make them an extremely compelling tool for employees and organizations alike. Indeed, a survey from PWC found that 79% of organizations have already adopted browser agents today. 

Yet, Browser AI Agents expose organizations to a massive security risk. These agents are trained to complete the tasks they are instructed to do, with little to no understanding of the security implications of their actions. Unlike human employees, Browser AI Agents are not subject to regular security awareness training. They cannot recognize visual warning signs like suspicious URLs, excessive permission requests, or unusual website designs that typically alert employees of a malicious site. Consequently, Browser AI Agents are more likely to fall prey to browser-based attacks than even a regular employee. Even if it is possible for users to add these guardrails, the overhead required to extensively write the security risk of every task performed by the agent in every prompt would probably outweigh the productivity gains. More importantly, employees using Browser AI Agents are unlikely to have enough security expertise to be able to write such a prompt in the first place.  

With the popular open-source Browser Use framework used by thousands of organizations, SquareX demonstrated how the Browser AI Agent, instructed to find and register for a file-sharing tool, succumbed to an OAuth attack. In the process of completing its task, it granted a malicious app complete access to the user’s email despite multiple suspicious signals – irrelevant permissions, unfamiliar brands, suspicious URLs – that likely would have stopped most employees from granting these permissions. In other scenarios, these agents might expose the user’s credit card information to a phishing site while trying to purchase groceries or disclose sensitive data when responding to emails from an impersonation attack. 

Unfortunately, neither browsers nor traditional security tools can differentiate between actions performed by users and these agents. Thus, it is critical for enterprises working with Browser AI Agents to provide browser-native guardrails that will prevent agents and employees alike from falling prey to these attacks.

> Vivek Ramachandran, Founder & CEO of SquareX, warns, “The arrival of Browser AI Agents have dethroned employees as the weakest link within organizations. Optimistically, these agents have the security awareness of an average employee, making them vulnerable to even the most basic attacks, let alone bleeding-edge ones. Critically, these Browser AI Agents are running on behalf of the user, with the same privilege level to access enterprise resources. Until the day browsers develop native guardrails for Browser AI Agents, enterprises must incorporate browser-native solutions like Browser Detection and Response to prevent these agents from being tricked into performing malicious tasks. Eventually, the new generation of identity and access management tools will also have to take into account Browser AI Agent identities to implement granular access controls on agentic workflows.”

To learn more about this security research, users can visit http://sqrx.com/browser-ai-agents .

SquareX’s research team is also holding a webinar on **July 11, 10am PT/1pm ET** to dive deeper into the research findings. To register, users can click here. 

**About SquareX**

SquareX’s browser extension turns any browser on any device into an enterprise-grade secure browser. SquareX’s industry-first Browser Detection and Response (BDR) solution empowers organizations to proactively detect, mitigate, and threat-hunt client-side web attacks, including malicious browser extensions, advanced spearphishing, browser-native ransomware, genAI DLP, and more. Unlike legacy security approaches and cumbersome enterprise browsers, SquareX seamlessly integrates with users’ existing consumer browsers, ensuring enhanced security without compromising user experience or productivity. By delivering unparalleled visibility and control directly within the browser, SquareX enables security leaders to reduce their attack surface, gain actionable intelligence, and strengthen their enterprise cybersecurity posture against the newest threat vector – the browser. Find out more on www.sqrx.com.

**Contact**

**Head of PR**  
**Junice Liew**  
**SquareX**  
**\[email protected\]**

SquareX Reveals that Employees are No Longer the Weakest Link, Browser AI Agents Are

AT&T is set to pay $177 million to customers affected by two significant data breaches. Were you affected and how can you submit your claim?

AT&T is set to pay $177 million to customers affected by two significant data breaches. These breaches exposed sensitive personal information of millions of current and former AT&T customers.

For those that have missed the story so far:

*   Back in 2021, an entity named Shiny Hunters (a known hacking group) claimed to have breached AT&T. Later reports indicated this breach started in 2019. AT&T denied that the data came from its systems.
*   Then in March, 2024, the data of over 70 million people was posted for sale on an online cybercrime forum. The seller claimed the data came from the Shiny Hunters breach. AT&T again denied the data came from its systems.
*   On March 30, 2024, AT&T reset customer passcodes after a security researcher discovered the encrypted login passcodes found in the leaked data were easy to decipher.
*   Finally, on April 2, 2024, AT&T confirmed that 73 million current and former customers had been caught up in the data leak.
*   A later breach, revealed in July, 2024, involved a hack of AT&T’s cloud storage provider, Snowflake, compromising call and text records from 2022 for nearly 109 million US customers. Although no names were linked to this data, the breach was severe enough to lead to arrests.

Following these incidents, AT&T faced multiple class action lawsuits alleging inadequate protection of customer data. Now, a US District Judge has granted preliminary approval to a settlement resolving these lawsuits. This settlement offers an opportunity for affected customers to receive compensation for the harm caused by these breaches.

**Who qualifies for compensation?**

*   Any current or former AT&T customer whose data was accessed in either breach is eligible.
*   Priority and larger payments will go to those who can document damages directly caused by the breaches.
*   Maximum payouts are up to $5,000 for the 2019 breach and $2,500 for the 2024 breach.
*   Any remaining funds will be distributed to others affected, even without proof of damages.

The projected timeline for the claims process looks like this

*   Notices to eligible claimants will be sent by August 4, 2025.
*   The deadline to submit claims is November 18, 2025.
*   Payments are expected to begin in early 2026, pending final court approval scheduled for December 3, 2025.

**Check if your data was exposed**

To find out how to claim, watch for official notifications from AT&T or check the settlement website once it launches.

You can use Malwarebytes’ easy, free tool—the Malwarebytes Digital Footprint Portal—to check if your data was exposed in the AT&T breach. Simply click the button below, enter your email address, and follow the prompts on the screen.

When you get your results, you’ll see a pink bubble with the words “Exposed on AT&T” if your information was affected in the breach. If you see a green bubble then your data was not exposed.

We will keep you posted of any new developments in this case. Stay tuned!

**We don’t just report on threats – we help safeguard your entire digital identity**

Cybersecurity risks should never spread beyond a headline. Protect your—and your family’s—personal information by using identity protection.

 AT&amp;T to pay compensation to data breach victims. Here&#8217;s how to check if you were affected 

Unidentified hackers breached a Norwegian dam's control system in April, opening its valve for hours due to a weak password. Learn how simple vulnerabilities threaten critical infrastructure.

In a concerning incident this April, unidentified hackers managed to breach the control systems of a Norwegian dam. Reportedly, hackers breached the control systems of a Norwegian dam, causing its water valve to open fully. The incident occurred at the Lake Risevatnet dam, situated near the city of Svelgen in Southwest Norway. The valve remained open for four hours before the unauthorized activity was detected.

According to the Norwegian energy news outlet, Energiteknikk, the hack did not pose a danger, as the water flow barely exceeded the dam’s minimum requirement. The valve released an additional 497 litres per second, but officials noted that the riverbed could handle a much larger volume, up to 20,000 litres per second.

****Vulnerable Control Systems Highlighted****

The incident was discovered on April 7 by the dam’s owner, Breivika Eiendom. Norwegian authorities, including NSM (National Security Authority), NVE (Norwegian Water Resources and Energy Directorate), and Kripos (a special agency of the Norwegian Police Service), were alerted on April 10, and an investigation is now underway.

Officials suspect the breach occurred because the valve’s web-accessible control panel was protected by a weak password. Breivika technical manager Bjarte Steinhovden speculated this was the likely vulnerability. The initial point of entry allowed attackers to bypass authentication controls and gain direct access to the operational technology (OT) environment.

****Broader Threats to Essential Services****

This incident is not isolated as such intrusions into vital infrastructure have occurred in the past. For instance, Hackread.com reported in April 2023, that Israel faced a wave of cyberattacks, with authorities believing they were part of OpIsrael, a campaign by pro-Palestinian hackers.

Among the targets were Israel’s irrigation systems, which saw several water monitors malfunction. The targets included irrigation and wastewater treatment systems in areas like the Hula Valley, the Jordan Valley, and the Galil Sewage Corporation. These cases show how simple vulnerabilities, like easy-to-guess passwords, can be exploited by threat actors.

****Lessons for Critical Infrastructure Protection****

While this particular facility primarily serves a fish farm and is not connected to Norway’s power grid, the incident shows a critical security lesson for essential infrastructure worldwide. It demonstrates how easily basic security failures, especially weak credentials, can compromise vital systems.

It also highlights that remote access, proper authentication, and clear ownership of cyber-physical interfaces should be standard security practices. The fact that the attack persisted for four hours undetected also indicates the importance of sufficient monitoring for critical infrastructure like dams. Effective cybersecurity practices, including strong passwords and multi-factor authentication (requiring more than one way to prove identity), are crucial for protecting these essential services.

Norwegian Dam Valve Forced Open for Hours in Cyberattack

Grocery giant Ahold Delhaize USA faced a major data breach affecting over 2.2 million employees. Learn what sensitive info was stolen and the ransomware group behind the Nov 2024 attack.

A data breach at Ahold Delhaize USA Services, LLC, a company providing support to the major East Coast grocery retailer Ahold Delhaize USA, has affected more than 2.2 million (2,242,521) individuals (including over 95,000 Mainers).

The incident, which involved unauthorized access to internal US business systems, occurred between November 5th and 6th, 2024, leading to the theft of highly sensitive personal, financial, and health information primarily belonging to current and former employees.

Ahold Delhaize USA is a prominent name in the US grocery sector, operating popular brands such as Food Lion, Giant Food, The GIANT Company, Hannaford, and Stop & Shop. According to Ahold Delhaize USA’s official statement, the company is notifying those impacted and is providing two years of complimentary credit monitoring and identity protection services. A help desk has also been established to assist individuals with inquiries.

****Details of the Cyberattack****

Ahold Delhaize USA Services detected the cybersecurity issue on November 6, 2024, and swiftly launched an investigation with the help of leading external cybersecurity experts., also coordinated with US federal law enforcement.

The investigation revealed that an unauthorized third party had gained access to and obtained files from one of their internal US file repositories. While the company quickly took some systems offline to contain the issue, leading to temporary disruptions for online orders and pharmacy services, these systems were soon restored.

The stolen data varied from person to person but was extensive, as per the breach notification submitted to the Maine Attorney General. It included names, contact details, dates of birth, government-issued identification numbers like Social Security numbers, passport numbers, and driver’s license numbers. Financial account records, including bank account numbers, were also compromised.

Additionally, health information, specifically workers’ compensation details and medical records within employment histories, along with other employment-related data, were exposed.

“Our review of the impacted files is still ongoing. At this time, we believe that many associates who were working for Ahold Delhaize Group, Ahold Delhaize Europe & Indonesia (EBS), Albert Heijn, Etos, Gall & Gall and the Ahold Delhaize Coffee Company in the Netherlands and who were on the payroll in April 2021 may have been affected by this issue,” the company noted.

Ahold Delhaize confirms that it found “no indication that customer payment or pharmacy systems were compromised” and “no customer credit card numbers contained in the affected files,” suggesting the focus of the attack was on employee data.

****Ransomware Group Claims Responsibility****

In a development that surfaced on April 16, 2025, the INC ransomware group publicly claimed responsibility for breaching Ahold Delhaize on their dark data leak website and threatened to release it fully after providing samples.

INC Ransomware on its dark web leak blog (Image: Hackread.com)

This group, active since mid-2023, often uses tactics like phishing emails or exploit kit malware to gain access. They are known for avoiding attacks in Russia, possibly indicating a base there or in a neighbouring country.

Ahold Delhaize confirmed on April 17, 2025, that data had indeed been stolen and began reviewing the affected files to identify the personal information at risk. This complex investigation, which has taken seven months to identify affected US individuals and also uncovered some Dutch employment data from April 2021, highlights the intricate nature of responding to such cyber incidents.

“To date, this is one of the most significant data breaches following a ransomware attack, particularly within the food and beverage sector,” said Rebecca Moody, Head of Data Research at Comparitech. “In fact, since we began tracking ransomware attacks at the start of 2018, this attack on Ahold Delhaize is the largest within the food and beverage sector (based on records affected).”

“In most cases, attacks on this sector have focused on system encryption, as this is often where the most disruption is caused. For example, from 2018 to the present, the average number of records breached in a ransomware attack on a food and beverage company was 53,200,_“_ explained Rebecca.

_“_This highlights the severity of this breach as well as the new focus on data theft (as well as system encryption) for the majority of ransomware gangs. It is likely that we’ll see larger data breaches within the food and beverage industry going forward. We are also yet to see the extent of the breaches on the UK’s Marks & Spencer and Co-op attacks this year.”

Ahold Delhaize Confirms Data Breach of 2.2M amid INC Ransomware Claims

Plus: US feds charge alleged masterminds behind infamous forum, Scattered Spider targets airlines, and hackers open a valve at a Norwegian dam.

WIRED published a shocking investigation this week based on records, including audio recordings, of hundreds of emergency calls from United States Immigration and Customs Enforcement (ICE) detention centers. The calls—which include reports of incidents of staff sexual assaults, suicide attempts, and head injuries—indicate a system inundated by life-threatening incidents, delayed treatment, and overcrowding.

In a 6-3 decision on Friday, the US Supreme Court upheld a Texas porn ID law, finding that age verification for explicit sites is constitutional. In a dissent, Justice Elena Kagan warned that this determination ignores First Amendment precedent and will have privacy implications for adults.

Looking at the US bombing of Iranian nuclear sites last weekend, President Donald Trump posted initial announcements of the strikes on the social Network Truth Social, which then began suffering intermittent outages. And WIRED reported on assessments of the damage to the nuclear sites based on satellite photos taken before and after the bombing.

Meanwhile, Taiwan is scrambling to make its own unmanned aerial vehicles domestically as drones increasingly become a crucial weapon of war. The urgency comes as a potential conflict with China looms. And Telegram launched a purge of Chinese cryptocurrency markets last month, banning black markets that sold tens of billions of dollars in crypto-scam-related services. Now, though, the markets are rebranding and bouncing back with no further action from the communication platform.

But wait, there’s more! Each week, we round up the security and privacy news we didn’t cover in depth ourselves. Click the headlines to read the full stories. And stay safe out there.

Immigration and Customs Enforcement (ICE) is now using a mobile app called Mobile Fortify that allegedly allows agents to identify individuals by pointing a smartphone at their face or capturing contactless fingerprints, 404 Media reports. The app reportedly taps into government databases, including Customs and Border Protection’s Traveler Verification Service and a DHS biometric intelligence system, in an attempt to match facial images taken in the field against prior government-collected records. ICE says the tool is intended to help officers identify “unknown subjects,” but civil liberties advocates tell 404 Media that it may open the door to surveillance-driven profiling and wrongful arrests.

Nathan Freed Wessler of the ACLU told the site, “Face recognition technology is notoriously unreliable, frequently generating false matches and resulting in a number of known wrongful arrests across the country. Immigration agents relying on this technology to try to identify people on the street is a recipe for disaster. Congress has never authorized DHS to use face recognition technology in this way, and the agency should shut this dangerous experiment down."

**US Feds Charge Group of Alleged Hackers Behind a Notorious Cybercrime Forum**

Global law enforcement this week announced the bust of a group of alleged cybercriminal hackers accused of carrying out years of profit-focused data breaches and running a notorious cybercriminal forum and market known as Breachforums. French authorities arrested four members of the group who went by the names “ShinyHunters,” “Hollow,” “Noct,” and “Depressed,” though the police sources who shared the news with the French newspaper Le Parisien didn’t reveal the suspects’ real names. The US Justice Department, meanwhile, criminally charged Kai West, a young British man, with carrying out a broad, years-long hacking spree under the handle “Intelbroker” that inflicted $25 million total damage against victims before he was arrested in February. In addition to hacking and selling vast troves of stolen data, the group—or at least some subset of its members—appears to have served as administrators for Breachforums, a notorious sales forum for cybercriminal information and tools that was shut down in a law enforcement operation in 2023 but was later relaunched by its staff.

**Scattered Spider Hackers Shift Their Targeting to the Airline Industry**

The loose cybercriminal gang known as Scattered Spider has carried out data theft and ransomware incidents for years, most recently targeting the grocery industry, other retailers, and the insurance industry in the US and the UK. Now cybersecurity analysts at Mandiant and Palo Alto Networks say the group is turning their attention to the aviation and transportation sector. Specifically, hackers were behind a cybersecurity incident last week that took down some IT systems and the mobile app for Canadian airline WestJet, Axios reports. Now Hawaiian Airlines has said it’s experiencing a “cybersecurity incident” affecting its network, though it hasn’t yet revealed more details or any evidence that Scattered Spider is responsible. Cybersecurity firms tracking the group warn that other potential aviation and transportation industry targets should be on the lookout for the group, which often uses sophisticated social engineering to trick staff into letting them bypass multi-factor authentication and gain a foothold on target systems.

**Hackers Breach a Norwegian Dam to Open Valve**

Here’s a curiosity that we missed a couple weeks ago: A rare industrial control system hijacking incident in which an unknown hacker appears to have messed with the computer systems that control the Lake Risevatnet dam in southwest Norway, opening a valve to its maximum setting. The tampering, the motivation for which was far from clear, increased the dam’s water flow by nearly 500 liters a second, but didn’t come close to approaching a dangerous level. No one appears to have spotted the change for close to four hours. Officials told the Norwegian energy news outlet Energiteknikk, which broke the story, that a weak password on a web-accessible control panel allowed the unauthorized access.

ICE Rolls Facial Recognition Tools Out to Officers' Phones

Cybercriminals use malicious AI models to write malware and phishing scams Cisco Talos warns of rising threats from uncensored and custom AI tools.

New research from Cisco Talos reveals a rise in cybercriminals abusing Large Language Models (LLMs) to enhance their illicit activities. These powerful AI tools, known for generating text, solving problems, and writing code, are, reportedly, being manipulated to launch more sophisticated and widespread attacks.

For your information, LLMs are designed with built-in safety features, including alignment (training to minimize bias) and guardrails (real-time mechanisms to prevent harmful outputs). For instance, a legitimate LLM like ChatGPT would refuse to generate a phishing email. However, cybercriminals are actively seeking ways around these protections.

Talos’s investigation, shared with Hackread.com highlights three primary methods used by adversaries:

**Uncensored LLMs**: These models, lacking safety constraints, readily produce sensitive or harmful content. Examples include OnionGPT and WhiteRabbitNeo, which can generate offensive security tools or phishing emails. Frameworks like Ollama allow users to run uncensored models, such as Llama 2 Uncensored, on their own machines.

**Custom-Built Criminal LLMs**: Some enterprising cybercriminals are developing their own LLMs specifically designed for malicious purposes. Names like GhostGPT, WormGPT, DarkGPT, DarkestGPT, and FraudGPT are advertised on the dark web, boasting features like creating malware, phishing pages, and hacking tools.

**Jailbreaking Legitimate LLMs**: This involves tricking existing LLMs into ignoring their safety protocols through clever prompt injection techniques. Methods observed include using encoded language (like Base64), appending random text (adversarial suffixes), role-playing scenarios (e.g., DAN or Grandma jailbreak), and even exploiting the model’s self-awareness (meta prompting).

The dark web has become a marketplace for these malicious LLMs. FraudGPT, for example, advertised features ranging from writing malicious code and creating undetectable malware to finding vulnerable websites and generating phishing content.

However, the market isn’t without its risks for criminals themselves; Talos researchers found that the alleged developer of FraudGPT, CanadianKingpin12, was scamming potential buyers out of cryptocurrency by promising a non-existent product.

Image via Cisco Talos

Beyond direct illicit content generation, cybercriminals are leveraging LLMs for tasks similar to legitimate users, but with a malicious twist. In December 2024, Anthropic, developers of Claude LLM, noted programming, content creation, and research as top uses for their model. Similarly, criminal LLMs are used for:

*   Programming: Crafting ransomware, remote access Trojans, wipers, and code obfuscation.

*   Content Creation: Generating convincing phishing emails, landing pages, and configuration files.

*   Research: Verifying stolen credit card numbers, scanning for vulnerabilities, and even brainstorming new criminal schemes.

LLMs are also becoming targets themselves. Attackers are distributing backdoored models on platforms like Hugging Face, embedding malicious code that runs when downloaded. Furthermore, LLMs that use external data sources (Retrieval Augmented Generation or RAG) can be vulnerable to data poisoning, where attackers manipulate the data to influence the LLM’s responses.

Cisco Talos anticipates that as AI technology continues to advance, cybercriminals will increasingly adopt LLMs to streamline their operations, effectively acting as a “force multiplier” for existing attack methods rather than creating entirely new “cyber weapons.”

Malicious AI Models Are Behind a New Wave of Cybercrime, Cisco Talos

A vulnerability was found in HKUDS LightRAG up to 1.3.8. It has been declared as critical. Affected by this vulnerability is the function upload_to_input_dir of the file lightrag/api/routers/document_routes.py of the component File Upload. The manipulation of the argument file.filename leads to path traversal. It is possible to launch the attack on the local host. The identifier of the patch is 60777d535b719631680bcf5d0969bdef79ca4eaf. It is recommended to apply a patch to fix this issue.

**Exploitability Metrics**

Attack Vector: This metric reflects the context by which vulnerability exploitation is possible. This metric value (and consequently the resulting severity) will be larger the more remote (logically, and physically) an attacker can be in order to exploit the vulnerable system. The assumption is that the number of potential attackers for a vulnerability that could be exploited from across a network is larger than the number of potential attackers that could exploit a vulnerability requiring physical access to a device, and therefore warrants a greater severity.

Attack Complexity: This metric captures measurable actions that must be taken by the attacker to actively evade or circumvent existing built-in security-enhancing conditions in order to obtain a working exploit. These are conditions whose primary purpose is to increase security and/or increase exploit engineering complexity. A vulnerability exploitable without a target-specific variable has a lower complexity than a vulnerability that would require non-trivial customization. This metric is meant to capture security mechanisms utilized by the vulnerable system.

Attack Requirements: This metric captures the prerequisite deployment and execution conditions or variables of the vulnerable system that enable the attack. These differ from security-enhancing techniques/technologies (ref Attack Complexity) as the primary purpose of these conditions is not to explicitly mitigate attacks, but rather, emerge naturally as a consequence of the deployment and execution of the vulnerable system.

Privileges Required: This metric describes the level of privileges an attacker must possess prior to successfully exploiting the vulnerability. The method by which the attacker obtains privileged credentials prior to the attack (e.g., free trial accounts), is outside the scope of this metric. Generally, self-service provisioned accounts do not constitute a privilege requirement if the attacker can grant themselves privileges as part of the attack.

User interaction: This metric captures the requirement for a human user, other than the attacker, to participate in the successful compromise of the vulnerable system. This metric determines whether the vulnerability can be exploited solely at the will of the attacker, or whether a separate user (or user-initiated process) must participate in some manner.

**Vulnerable System Impact Metrics**

Confidentiality: This metric measures the impact to the confidentiality of the information managed by the VULNERABLE SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.

Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the VULNERABLE SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).

Availability: This metric measures the impact to the availability of the VULNERABLE SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.

**Subsequent System Impact Metrics**

Confidentiality: This metric measures the impact to the confidentiality of the information managed by the SUBSEQUENT SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.

Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the SUBSEQUENT SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).

Availability: This metric measures the impact to the availability of the SUBSEQUENT SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.

GHSA-v9w6-9hq9-33ch: HKUDS LightRAG allows Path Traversal via function upload_to_input_dir

In a 6-3 decision, the Supreme Court held that age verification for explicit sites is constitutional. In a dissent, Justice Elena Kagan warned it burdens adults and ignores First Amendment precedent.

If you try to access Pornhub, one of the world’s biggest websites, from any of 17 US states, you’ll be blocked. Pornhub’s parent company, Aylo Holdings, has restricted access in response to a slew of laws that says Pornhub itself should be responsible for checking that every visitor is over 18. Now, the United States Supreme Court has made a decision on a key age verification law, which could have ramifications for the entire country and the wider internet as a whole.

On Friday, in a 6–3 decision that could reshape the landscape of online privacy and free speech, the Supreme Court upheld in full the Texas age verification law—one of the first passed in the country—requiring many websites publishing pornographic content to check that all visitors are over 18. The law, TX HB1181, says sites that are “more than one-third sexual material” can face fines of up to $10,000 per day if they don’t put in place age verification systems, plus extra penalties of up to $250,000. It also states websites should display health warnings about the potential health risks of pornography.

Writing for the majority, Justice Clarence Thomas said that because the law "simply requires proof of age to access content that is obscene to minors, it does not directly regulate adults’ protected speech," adding, "adults have no First Amendment right to avoid age verification."

In her dissent, Justice Elena Kagan argued that the Texas law imposes a direct and unconstitutional burden on adults’ access to protected speech. “A State may not care much about safeguarding adults’ access to sexually explicit speech; a State may even prefer to curtail those materials for everyone,” she wrote, “but the First Amendment protects those sexually explicit materials, for every adult.”

The ruling marks a major victory for Texas attorney general Ken Paxton, who defended the law amid fierce opposition from digital rights groups and the adult entertainment industry.

Legislators in Texas passed HB1181 in early 2023, but it was struck down in the US District Court for the Western District of Texas for potentially being unconstitutional before the law went into effect. Adult industry group the Free Speech Coalition, among others, challenged the Texas law on the grounds that it violates the First Amendment by restricting adults’ access to constitutionally protected speech. In March last year, a Fifth Circuit appeals court upheld the Texas law before the Free Speech Coalition took the case to the Supreme Court in a January hearing.

In recent years, a wave of age verification laws have been proposed in states across the country. More than half of US states have passed or have tried to pass age verification laws, according to a tracker published by the Free Speech Coalition.

“Efforts to regulate online pornography are often the opening move in broader campaigns to censor the internet,” Jess Miers, a visiting assistant professor of law at the University of Akron School of Law, said before the decision. “While this case focuses on mandatory age verification for adult content, state lawmakers are hoping it provides a legal foundation to impose sweeping restrictions on a wide range of online material.”

Attempts to get pornographic websites to implement age checks—more than just clicking a button saying you are over 18—have been accelerating over the past decade, since government officials in the UK passed laws on age verification checks only to delay and abandon them in 2019. Since then, though, a wave of companies and technologies selling age-checking software has rapidly expanded and matured. Adult websites and pornographers aren’t against introducing robust age checks; they say they don’t want children to be exposed to illicit content.

Multiple methods of age verification, which is often called age assurance, have been proposed or developed in recent years, with regulators and governments around the world pushing for them to be used to stop children accessing content that may not be suitable for them. These age verification methods can include, but aren’t limited to, checking someone’s identity against government ID, providing banking details, or using face-checking systems that can predict someone’s age.

Typically, third-party companies are developing the age-checking methods, with adult websites paying to use their services. This can mean people do not directly share their ID documents or other details used to verify their age directly with pornography websites or the companies that own them. Some companies, including Pornhub owner Aylo Holdings and Meta, have argued that age checks should happen by Google and Apple on their respective app stores. Those companies don’t agree.

Repeatedly, privacy and civil liberties experts have stated that any data collection or understanding of how people consume pornography could have devastating consequences if there’s a data breach or information is leaked. (One ID verification company suffered a data breach last year.) Unscrupulous companies could also sell or share data, privacy advocates say.

Last week, the preliminary results of an age checking trial in Australia, which has passed laws to ban under-16s from social media apps, found such systems may not be effective. Plus, age checks can often be easily circumvented by using a VPN. Aylo has claimed that current age verification proposals aren’t effective and push people to smaller websites, which may have fewer safety tools in place to moderate images and videos.

Despite potential concerns, laws mandating companies use age verification systems are being introduced around the world, and multiple companies are adopting the systems. Since 2022, Instagram has been using facial age estimation software to check people’s ages. In April, chat app Discord announced it is testing face scans in the UK and Australia. Regulators in Germany have been pursuing age checks—going as far as to fine individuals posting on X (then Twitter) in 2023—for years. Last week, Pornhub returned to France—it pulled services relating to the country’s age checking at the start of June—after a court ruling limited the law. And by July this year, porn sites and social media platforms operating in the UK are required to introduce “robust” age checks. Pornhub owner Aylo announced on Thursday that it would adopt "government approved age assurance methods” to comply with the law.

With the Supreme Court’s Friday decision, the threat to pornography and sexual expression in the country may be more grave. The Heritage Foundation’s Project 2025 plan, which has been partially followed by the US government, has suggested criminalizing pornography and shutting down its producers. Earlier this year, Senator Mike Lee of Utah proposed the Interstate Obscenity Definition Act, which could redefine what’s considered “obscene” content and potentially ban pornography entirely.

“Once the state has the authority to restrict access to adult content, it will almost certainly broaden the definition of ‘material harmful to minors,’” Miers says. “This could include reproductive health information, LGBTQ+ resources, and educational content related to race, gender, or diversity.”

_Additional reporting by Dell Cameron._

Tag

#web