Geek Guy

Category: Cybersecurity

Dive into deep-dive analysis on the evolving threat landscape, focusing on identity security (ITDR, NHI), data protection (DSPM), and agentic identity. Stay updated with expert insights on threat actor tactics and local AI security for researchers and market analysts.

When your mouse turns snitch, and hackers grow a conscience

Your computer’s mouse might not be as innocent as it looks – and one ransomware crew has a crisis of conscience that nobody saw coming. We talk about how something as ordinary as a web page could turn your mouse into a surprisingly nosey neighbour, and why ransomware gangs need to think carefully about their…

Voting groups ask court for immediate halt to Trump admin’s SAVE database overhaul

Voting rights groups are asking a court to block an ongoing Trump administration effort to merge disparate federal and state voter data into a massive citizenship and voter fraud database. Last week, the League of Women Voters, the Electronic Privacy Information Center (EPIC) and five individuals sued the federal government in D.C. District Court, saying…

Voting groups ask court for immediate halt to Trump admin’s SAVE database overhaul

Voting rights groups are asking a court to block an ongoing Trump administration effort to merge disparate federal and state voter data into a massive citizenship and voter fraud database. Last week, the League of Women Voters, the Electronic Privacy Information Center (EPIC) and five individuals sued the federal government in D.C. District Court, saying…

Voting groups ask court for immediate halt to Trump admin’s SAVE database overhaul

Voting rights groups are asking a court to block an ongoing Trump administration effort to merge disparate federal and state voter data into a massive citizenship and voter fraud database. Last week, the League of Women Voters, the Electronic Privacy Information Center (EPIC) and five individuals sued the federal government in D.C. District Court, saying…

Voting groups ask court for immediate halt to Trump admin’s SAVE database overhaul

Voting rights groups are asking a court to block an ongoing Trump administration effort to merge disparate federal and state voter data into a massive citizenship and voter fraud database. Last week, the League of Women Voters, the Electronic Privacy Information Center (EPIC) and five individuals sued the federal government in D.C. District Court, saying…

Voting groups ask court for immediate halt to Trump admin’s SAVE database overhaul

Voting rights groups are asking a court to block an ongoing Trump administration effort to merge disparate federal and state voter data into a massive citizenship and voter fraud database. Last week, the League of Women Voters, the Electronic Privacy Information Center (EPIC) and five individuals sued the federal government in D.C. District Court, saying…

How to Grow SOC Team Expertise for Ultimate Triage & Response Speed 

Building analyst expertise takes time, often too much… Most new hires need over six months before they can handle complex incidents with confidence, leaving senior analysts to pick up the slack and slowing the entire SOC down.  Traditional training programs can’t keep pace with real attacks. Theories and simulations don’t prepare teams for fast, messy, real-world…

Microsoft pins GoAnywhere zero-day attacks to ransomware affiliate Storm-1175

Microsoft Threat Intelligence said a cybercriminal group it tracks as Storm-1175 has exploited a maximum-severity vulnerability in GoAnywhere MFT to initiate multi-stage attacks including ransomware. Researchers observed the malicious activity Sept. 11, Microsoft said in a blog post Monday. Microsoft’s research adds another substantive chunk of evidence to a growing collection of intelligence confirming the…

Microsoft pins GoAnywhere zero-day attacks to ransomware affiliate Storm-1175

Microsoft Threat Intelligence said a cybercriminal group it tracks as Storm-1175 has exploited a maximum-severity vulnerability in GoAnywhere MFT to initiate multi-stage attacks including ransomware. Researchers observed the malicious activity Sept. 11, Microsoft said in a blog post Monday. Microsoft’s research adds another substantive chunk of evidence to a growing collection of intelligence confirming the…

Microsoft pins GoAnywhere zero-day attacks to ransomware affiliate Storm-1175

Microsoft Threat Intelligence said a cybercriminal group it tracks as Storm-1175 has exploited a maximum-severity vulnerability in GoAnywhere MFT to initiate multi-stage attacks including ransomware. Researchers observed the malicious activity Sept. 11, Microsoft said in a blog post Monday. Microsoft’s research adds another substantive chunk of evidence to a growing collection of intelligence confirming the…

Microsoft pins GoAnywhere zero-day attacks to ransomware affiliate Storm-1175

Microsoft Threat Intelligence said a cybercriminal group it tracks as Storm-1175 has exploited a maximum-severity vulnerability in GoAnywhere MFT to initiate multi-stage attacks including ransomware. Researchers observed the malicious activity Sept. 11, Microsoft said in a blog post Monday. Microsoft’s research adds another substantive chunk of evidence to a growing collection of intelligence confirming the…

Microsoft pins GoAnywhere zero-day attacks to ransomware affiliate Storm-1175

Microsoft Threat Intelligence said a cybercriminal group it tracks as Storm-1175 has exploited a maximum-severity vulnerability in GoAnywhere MFT to initiate multi-stage attacks including ransomware. Researchers observed the malicious activity Sept. 11, Microsoft said in a blog post Monday. Microsoft’s research adds another substantive chunk of evidence to a growing collection of intelligence confirming the…

OpenAI: Threat actors use us to be efficient, not make new tools

A long-running theme in the use of adversarial AI since the advent of large language models has been the automation and enhancement of well-established hacking methods, rather than the creation of new ones.   That remains the case for much of OpenAI’s October threat report, which highlights how government agencies and the cybercriminal underground are opting…

OpenAI: Threat actors use us to be efficient, not make new tools

A long-running theme in the use of adversarial AI since the advent of large language models has been the automation and enhancement of well-established hacking methods, rather than the creation of new ones.   That remains the case for much of OpenAI’s October threat report, which highlights how government agencies and the cybercriminal underground are opting…

OpenAI: Threat actors use us to be efficient, not make new tools

A long-running theme in the use of adversarial AI since the advent of large language models has been the automation and enhancement of well-established hacking methods, rather than the creation of new ones.   That remains the case for much of OpenAI’s October threat report, which highlights how government agencies and the cybercriminal underground are opting…

OpenAI: Threat actors use us to be efficient, not make new tools

A long-running theme in the use of adversarial AI since the advent of large language models has been the automation and enhancement of well-established hacking methods, rather than the creation of new ones.   That remains the case for much of OpenAI’s October threat report, which highlights how government agencies and the cybercriminal underground are opting…

OpenAI: Threat actors use us to be efficient, not make new tools

A long-running theme in the use of adversarial AI since the advent of large language models has been the automation and enhancement of well-established hacking methods, rather than the creation of new ones.   That remains the case for much of OpenAI’s October threat report, which highlights how government agencies and the cybercriminal underground are opting…

Phishing, Cloud Abuse, and Evasion: Advanced OSINT Investigation with ANY.RUN Threat Intelligence 

Editor’s note: The current article is authored by Clandestine, threat researcher and threat hunter. You can find Clandestine on X.  ANY.RUN’s Threat Intelligence (TI) Lookup is a powerful service for Open Source Intelligence (OSINT) and Threat Intelligence investigations. In this research, we shall analyze 5 specific queries, each targeting different aspects of the threat landscape, to better…

Oracle zero-day defect amplifies panic over Clop’s data theft attack spree

Federal cyber authorities and threat hunters are on edge following Oracle’s Saturday disclosure of an actively exploited zero-day vulnerability the Clop ransomware group used to initiate a widespread data theft and extortion campaign researchers initially warned about last week.  Oracle addressed the critical vulnerability — CVE-2025-61882 affecting Oracle E-Business Suite — in a security advisory…

Oracle zero-day defect amplifies panic over Clop’s data theft attack spree

Federal cyber authorities and threat hunters are on edge following Oracle’s Saturday disclosure of an actively exploited zero-day vulnerability the Clop ransomware group used to initiate a widespread data theft and extortion campaign researchers initially warned about last week.  Oracle addressed the critical vulnerability — CVE-2025-61882 affecting Oracle E-Business Suite — in a security advisory…

Oracle zero-day defect amplifies panic over Clop’s data theft attack spree

Federal cyber authorities and threat hunters are on edge following Oracle’s Saturday disclosure of an actively exploited zero-day vulnerability the Clop ransomware group used to initiate a widespread data theft and extortion campaign researchers initially warned about last week.  Oracle addressed the critical vulnerability — CVE-2025-61882 affecting Oracle E-Business Suite — in a security advisory…

Deeper Network Promo Deeper Network Promo Deeper Network Promo Image

Oracle zero-day defect amplifies panic over Clop’s data theft attack spree

Federal cyber authorities and threat hunters are on edge following Oracle’s Saturday disclosure of an actively exploited zero-day vulnerability the Clop ransomware group used to initiate a widespread data theft and extortion campaign researchers initially warned about last week.  Oracle addressed the critical vulnerability — CVE-2025-61882 affecting Oracle E-Business Suite — in a security advisory…

Oracle zero-day defect amplifies panic over Clop’s data theft attack spree

Federal cyber authorities and threat hunters are on edge following Oracle’s Saturday disclosure of an actively exploited zero-day vulnerability the Clop ransomware group used to initiate a widespread data theft and extortion campaign researchers initially warned about last week.  Oracle addressed the critical vulnerability — CVE-2025-61882 affecting Oracle E-Business Suite — in a security advisory…

Potential EU law sparks global concerns over end-to-end encryption for messaging apps 

Tech experts and companies offering encrypted messaging services are warning that  pending European regulation, which would grant governments broad authority to scan messages and content on personal devices for criminal activity, could spell “the end” of privacy in Europe. The European Union will vote Oct. 14 on a legislative proposal from the Danish Presidency known…

Potential EU law sparks global concerns over end-to-end encryption for messaging apps 

Tech experts and companies offering encrypted messaging services are warning that  pending European regulation, which would grant governments broad authority to scan messages and content on personal devices for criminal activity, could spell “the end” of privacy in Europe. The European Union will vote Oct. 14 on a legislative proposal from the Danish Presidency known…

Potential EU law sparks global concerns over end-to-end encryption for messaging apps 

Tech experts and companies offering encrypted messaging services are warning that  pending European regulation, which would grant governments broad authority to scan messages and content on personal devices for criminal activity, could spell “the end” of privacy in Europe. The European Union will vote Oct. 14 on a legislative proposal from the Danish Presidency known…

Potential EU law sparks global concerns over end-to-end encryption for messaging apps 

Tech experts and companies offering encrypted messaging services are warning that  pending European regulation, which would grant governments broad authority to scan messages and content on personal devices for criminal activity, could spell “the end” of privacy in Europe. The European Union will vote Oct. 14 on a legislative proposal from the Danish Presidency known…

Potential EU law sparks global concerns over end-to-end encryption for messaging apps 

Tech experts and companies offering encrypted messaging services are warning that  pending European regulation, which would grant governments broad authority to scan messages and content on personal devices for criminal activity, could spell “the end” of privacy in Europe. The European Union will vote Oct. 14 on a legislative proposal from the Danish Presidency known…

Security leaders at Okta and Zscaler share lessons from Salesloft Drift attacks

When security researchers issued warnings about the Salesloft Drift issues last month, two prominent cybersecurity companies found themselves facing the same threat — but their stories ended up unfolding in different ways.  Okta and Zscaler, among the larger players in the identity management space, were among the more than 700 Drift customers targeted in what…

Security leaders at Okta and Zscaler share lessons from Salesloft Drift attacks

When security researchers issued warnings about the Salesloft Drift issues last month, two prominent cybersecurity companies found themselves facing the same threat — but their stories ended up unfolding in different ways.  Okta and Zscaler, among the larger players in the identity management space, were among the more than 700 Drift customers targeted in what…

Security leaders at Okta and Zscaler share lessons from Salesloft Drift attacks

When security researchers issued warnings about the Salesloft Drift issues last month, two prominent cybersecurity companies found themselves facing the same threat — but their stories ended up unfolding in different ways.  Okta and Zscaler, among the larger players in the identity management space, were among the more than 700 Drift customers targeted in what…

Security leaders at Okta and Zscaler share lessons from Salesloft Drift attacks

When security researchers issued warnings about the Salesloft Drift issues last month, two prominent cybersecurity companies found themselves facing the same threat — but their stories ended up unfolding in different ways.  Okta and Zscaler, among the larger players in the identity management space, were among the more than 700 Drift customers targeted in what…

Security leaders at Okta and Zscaler share lessons from Salesloft Drift attacks

When security researchers issued warnings about the Salesloft Drift issues last month, two prominent cybersecurity companies found themselves facing the same threat — but their stories ended up unfolding in different ways.  Okta and Zscaler, among the larger players in the identity management space, were among the more than 700 Drift customers targeted in what…

Release Notes: Palo Alto Networks, Microsoft, IBM Connectors and 2,300+ Suricata Rules

September brought big updates to ANY.RUN. From four new connectors that plug our sandbox and threat intelligence straight into the world’s top SIEM and SOAR platforms, to a redesigned Threat Intelligence Lookup home screen built for speed and simplicity, your SOC now works smarter and faster than ever.   Add in 99 fresh signatures, 11 new YARA rules, and 2,322…

Salesforce’s trusted domain of doom

Researchers uncovered a security flaw in Salesforce’s shiny new Agentforce. The vulnerability, dubbed “ForcedLeak”, let them smuggle AI-read instructions in via humble Web-to-Lead form… and ended up spilling data for the low, low price of five dollars. And we discuss why data breach communications still default to “we take security seriously” while quietly implying “assume no…

FunkSec’s FunkLocker: How AI Is Powering the Next Wave of Ransomware 

Editor’s note: The current article is authored by Mauro Eldritch, offensive security expert and threat intelligence analyst. You can find Mauro on X.  AI is part of our lives whether we like it or not. Even if you are not quite a fan, or not a user at all, you probably came across multiple AI-generated avatars, pictures,…

ANY.RUN & MS Defender: Enrich Alerts Faster, Stop Attacks Early 

Lack of context makes it hard for Security Operations Centers (SOC) to tell actual threats from false positives. ANY.RUN’s connectors for Microsoft Defender bridge this gap by automating interactive sandbox analysis and providing real-time threat intelligence for correlation.   As a result, security teams achieve faster incident resolution, reduced alert fatigue, and proactive threat detection all…

ANY.RUN Sandbox & Microsoft Sentinel: Less Noise, More Speed for Your SOC

SOC teams may waste hours daily manually enriching alerts and switching between tools, delaying response. ANY.RUN’s Microsoft Sentinel Connector fixes this by introducing fast, accurate, and interactive sandbox analysis into Sentinel’s workflow, so alerts get auto-processed, enriched with IOCs, and prioritized in seconds.   Here’s how you can speed up response times, filter out false positives,…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Guarding your family against the latest online threats

Parents across America face a growing wave of sophisticated online fraud designed to exploit their deepest fears and protective instincts. Americans reported losing more than $12.5 billion to fraud in 2024, representing a 25% increase over the prior year, according to new Federal Trade Commission data. Parents represent a particularly vulnerable target because scammers understand…

Fighting Telecom Cyberattacks: Investigating a Campaign Against UK Companies

Telecommunications companies are the digital arteries of modern civilization. Compromise a major telecom operator, and you don’t just steal data — you gain the power to intercept communications, manipulate network traffic, and bring entire regions offline.  Every day, ANY.RUN’s solutions process thousands of threat samples, and hidden within them are patterns of activity targeting telecom operators.…

Efficient SOC: How to Detect and Solve Incidents Faster 

SOCs face constant pressure. Heavy workloads, poor threat visibility, and disconnected tools introduce delays in detection and response, which may lead to financial loss and operational disruptions for the business.  ANY.RUN helps over 15K security teams to solve this challenge by empowering them to quickly detect, analyze, and understand threats, so they can respond faster…

Efficient SOC: How to Detect and Solve Incidents Faster 

SOCs face constant pressure. Heavy workloads, poor threat visibility, and disconnected tools introduce delays in detection and response, which may lead to financial loss and operational disruptions for the business.  ANY.RUN helps over 15K security teams to solve this challenge by empowering them to quickly detect, analyze, and understand threats, so they can respond faster…

ANY.RUN & Palo Alto Networks Cortex XSOAR: Streamline SOC Workflows for Top Performance 

Swamped by incident alerts, Security Operations Centers (SOCs) struggle to quickly identify and prioritize high-risk attacks, leaving critical infrastructure exposed to ransomware and data theft. ANY.RUN’s integration with Palo Alto Networks Cortex XSOAR solves this by automating proactive sandbox analysis and threat intelligence correlation to beat alert fatigue, boost detection rates, and accelerate security workflows. …

Deeper Network Promo Deeper Network Promo Deeper Network Promo Image

ANY.RUN & Palo Alto Networks Cortex XSOAR: Streamline SOC Workflows for Top Performance 

Swamped by incident alerts, Security Operations Centers (SOCs) struggle to quickly identify and prioritize high-risk attacks, leaving critical infrastructure exposed to ransomware and data theft. ANY.RUN’s integration with Palo Alto Networks Cortex XSOAR solves this by automating proactive sandbox analysis and threat intelligence correlation to beat alert fatigue, boost detection rates, and accelerate security workflows. …

SonicWall firewalls targeted by fresh Akira ransomware surge

Researchers and authorities are warning that Akira ransomware attacks involving exploits of a year-old vulnerability affecting SonicWall firewalls are on the rise.  A burst of about 40 attacks linked to CVE-2024-40766 hit SonicWall firewalls between mid-July and early August. Researchers have since observed another wave of ransomware attacks linked to active exploits of the defect,…

Wyden calls on FTC to investigate Microsoft for ‘gross cybersecurity negligence’ in protecting critical infrastructure

Sen. Ron Wyden, D-Ore., on Wednesday called for the Federal Trade Commission to investigate Microsoft, saying the company’s default configurations are leaving customers vulnerable and contributing to ransomware, hacking and other threats. That includes the 2024 Ascension hospital ransomware attack, which resulted in the theft of personal data, medical data, payment information, insurance information and…

The npm incident frightened everyone, but ended up being nothing to fret about

Security professionals and observers across the industry got swept into a pit of fear Monday when an attacker took over and injected malicious code into a series of widely used open-source packages in the node.js package manager, or npm. Despite all that worry, the disaster that many presumed a foregone conclusion was averted and the…

Apple’s new Memory Integrity Enforcement system deals a huge blow to spyware developers

Apple has unveiled a comprehensive security system called Memory Integrity Enforcement (MIE) that represents a five-year engineering effort to combat sophisticated cyberattacks targeting individual users through memory corruption vulnerabilities. The technology is built into Apple’s new iPhone 17 and iPhone Air devices, as well as the A19 and A19 Pro chips. It combines custom-designed hardware…

Lazarus Group Attacks in 2025: Here’s Everything SOC Teams Need to Know 

The Lazarus Group, North Korea’s state-sponsored hacking collective, has held the title of the most notorious advanced persistent threat (APT) for almost two decades now. In 2025, it escalated its cyber operations, targeting tech industries with fake IT workers, fraudulent job interviews, and hijacked open-source software.   It’s time to take a closer look at its…

Lazarus Group Attacks in 2025: Here’s Everything SOC Teams Need to Know 

The Lazarus Group, North Korea’s state-sponsored hacking collective, has held the title of the most notorious advanced persistent threat (APT) for almost two decades now. In 2025, it escalated its cyber operations, targeting tech industries with fake IT workers, fraudulent job interviews, and hijacked open-source software.   It’s time to take a closer look at its…

Microsoft Patch Tuesday addresses 81 vulnerabilities, none actively exploited

Microsoft addressed 81 vulnerabilities affecting its enterprise products and underlying Windows systems, but none have been actively exploited, the company said in its latest security update.  The company’s monthly bundle of patches includes one high-severity vulnerability and eight critical defects, including three designated as more likely to be exploited.  The most severe defect disclosed this…

U.S. indicts Ukrainian national for hundreds of ransomware attacks using multiple variants

The Department of Justice unsealed an indictment against a Ukrainian national alleged to be central to a ransomware campaign affecting hundreds of companies worldwide.  Volodymyr Viktorovych Tymoshchuk, known online as “deadforz,” “Boba,” “msfv,” and “farnetwork,” is accused of developing and deploying ransomware variants Nefilim, LockerGoga, and MegaCortex, all of which have been used in attacks…

Former Meta security chief sues company for privacy violations, professional retaliation

Meta is being sued by its former head of security, who claims the company ignored repeated warnings that its messaging platform WhatsApp was riddled with security vulnerabilities and privacy violations, and retaliated against him for raising these concerns, ultimately firing him. Attaullah Baig was the head of security at Meta from 2021 until this past…

ANY.RYN x IBM QRadar SIEM: Real-Time Intelligence for Wider Threat Coverage 

ANY.RUN’s Threat Intelligence Feeds are designed to power SOAR, SIEM, EDR/XDR, TIP, and other security systems. Our goal is simple: to fit naturally into a customer’s security ecosystem so analysts can investigate incidents faster, improve detection quality, and spend less time on repetitive tasks.  Now, IBM QRadar SIEM users can directly consolidate ANY.RUN’s Threat Intelligence…

Treasury Department targets Southeast Asia scam hubs with sanctions

Federal authorities on Monday imposed sanctions on 19 people and organizations allegedly involved in major cyberscam hubs in Burma and Cambodia. “Criminal actors across Southeast Asia have increasingly exploited the vulnerabilities of Americans online,” Secretary of State Marco Rubio said in a statement. “In 2024, Americans lost at least $10 billion to scam operations in…

Salesloft Drift security incident started with undetected GitHub access

Salesloft pinned the root cause of the Drift supply-chain attacks to a threat group gaining access to its GitHub account as far back as March, the company said in an update Saturday.  During a 10-day period in mid-August, the threat group compromised and stole data from hundreds of organizations.  The threat group, which Google tracks…

NYU team behind AI-powered malware dubbed ‘PromptLock’ 

Researchers at New York University have taken credit for creating a piece of malware found by third-party researchers that uses prompt injection to manipulate  a large language model into assisting with a ransomware attack. Last month, researchers at ESET claimed to have discovered the first piece of “AI-powered ransomware” in the wild, flagging code found…