#Aihacking

Off-the-Shelf AI Models Are Getting Good at Hacking, Too Nine months ago, Forescout's researchers found just three AI models could produce a working exploit; now it's more than half.

Anthropic’s “superhacker” Mythos might not be in public hands, but a new study from Forescout has revealed that widely available, off-the-shelf LLMs could be just as dangerous.

www.digit.fyi/off-the-shel...
#tech #Mythos #Aihacking #vibehacking @Forescout

Anthropic’s new AI tool has implications for us all – whether we can use it or not | Shakeel Hashim via US news | The Guardian — Claude Mythos’s apparent superhuman hacking abilities are alarming experts as the Trump administration remains blinded by hostility In June 2024, a cyber-attack on a pathology services company caused chaos across London’s hospitals. More than 10,000 appointments were cancelled. Blood shortages followed and delays to blood tests led to a patient’s death . Lethal cyber-attacks like this are thankfully rare. But a new AI release could change that – plunging us into a terrifying new world of chaos a

Anthropic's new AI, Claude Mythos, reportedly exhibits superhuman hacking abilities, raising concerns amid potential for increased cyberattacks and real-world co...

Brought to you by resist47.news — tracking threats to democracy.

#resist47 #ClaudeMythos
#AIHacking
#CyberSecurityThreat
#AnthropicAI

Anthropic’s New AI Is Too Good at Hacking Mythos discovered thousands of long‑hidden exploits, outperforming all but the most skilled human experts in vulnerability discovery.

Anthropic has launched a new security initiative alongside big tech partners, including Amazon, Apple, Google, and Microsoft, after the AI firm found its latest model was far too good at finding and exploiting software vulnerabilities.

www.digit.fyi/anthropics-n...
#Anthropic #Mythos #AIhacking

AI agents are running wild, causing chaos – so why isn’t anyone stopping them? An AI agent hacking a government system and stealing millions of people’s data sounds like science fiction. But this recently happened and it’s not the only incident either. As experts warn AI is edgi...

#AI #agents are running #wild, causing #chaos – so why isn’t anyone stopping them? #AIAgents #Code #Hacking #AIHacking #Security #Data #Databreach #Privacy #ClaudeCode #Agentic #cyberattack #Alibaba #crypto #AgenticAI (#release #PANDORA #fix😱) #Meta #Military😱
www.independent.co.uk/news/ai-agen...

This Startup’s AI Beat 99% Of Humans In Six Elite Hacking Competitions www.forbes.com/sites... #cybersecurity #AI #AIHacking #OffensiveSecurity #AIAgent #AgenticAI #Tenzai #CTF

Know an #AI enthusiast or tinkerer in the Bay Area who would benefit from attending NEBULA:FOG SINGULARITY this Saturday?

Share this with them. We've still got a few spots left.
nebulafog.ai/register.html

#AIHacking #AIHackathon #Hackathon

2026-03-09 Briefing Data breaches continue to plague online platforms, with Roblox users facing exposure of 50 million login records and Cal AI, recently promoted by MrBeast, reporting a breach affecting 3 million subscribers. Simultaneously, a critical vulnerability in NGINX UI allows hackers to download system backups, emphasizing the need for immediate software updates. Elsewhere, AI startup Nscale secured $2 billion in funding, achieving a $14.6 billion valuation and attracting significant investment from Nvidia, alongside former Meta executives joining the board.

Tech News Briefing — #DarkWebSecurity
#RobloxSecurity
#AIHacking
#CybersecurityBreach
#DigitalSecurityThreats
#DataPrivacyMatters → https://alobbs.com/post/2026-03-09/

Zero Trust Home Network: AI Breaks Flat WiFi in Minutes Evil twins, AirSnitch isolation bypass, AI-powered exploit chaining, and NAS zero-days make flat home networks a red team playground in 2026.

parked curbside. one command. AI agent cloned the WiFi, ran the deauth flood, bypassed client isolation, and got root on the NAS in 20 minutes. no pentester required. #AIHacking #WiFiSecurity full chain: www.toxsec.com/p/zero-trust...

I hacked ChatGPT and Google s AI – and it only took 20 minutes I found a way to make AI tell you lies – and I m not the only one.

What would you ask an AI if you knew it could lie? I hacked ChatGPT and Google AI in just 20 minutes! #AIhacking

www.bbc.com/future/article/20260218-...

The Viral AI Agent Blowing Up the Internet… But It Could Hack Your Entire Computer Overnight

www.youtube.com/shorts/-SJDX...

#Moltbot, #AIagent, #viralAI
#opensourceAI, #AIsecurityrisk, #AIhacking, #AIbackdoor, #promptinjection, #GitHubstars, #Cloudflarestock, #AInews, #technews

Penligent AI New Update
AI hacker for cybersecurity, has rolled out exciting new features like faster agentic pentesting
youtu.be/8xrRP3q4ceQ?...
#Arlington #thetraitorsUS #FridayVibes #BugBounty #Pentesting #AIHacking #Penligent #cybersecurity

🤖 AI just found its first zero-day vulnerability.
CVE-2025-54322 affects 70,000+ industrial network devices worldwide. No authentication needed. Root access.
Full Details - www.cyberkendra.com/2025/12/ai-a...
#Cybersecurity #AI #ZeroDay #InfoSec #IndustrialSecurity #TechNews #AIHacking

🛡️ If you’re a cybersecurity specialist ready to freelance, Realancer is built for you — join the waitlist now: realancer.net/registration

👉 Read the full story here: alitech.io/blog/an-18-a...

#AI #ArtificialIntelligence #CyberSecurity #AIHacking #EthicalHacking #AlitechSolutions #Realancer

BSidesVienna 0x7E9 Sat, Nov. 22, 2025

It seems like some people could not make it after all and returned their #BSidesVienna ticket and their workshop ticket. There are now free seats again for #lockpicking and #AIHacking tickets.bsidesvienna.at/7e9/

Anthropic AI used in state backed hacking Things just got even scarier for your clients

The US artificial intelligence developer, Anthropic, has disrupted the first documented state-sponsored cyber-espionage campaign driven largely by autonomous #AI. Is this what the future of hacking will be?
#CyberSecurity #AIHacking #CyberAttack

Russian hackers just turned Claude into a one‑click malware factory—80‑90% of the attack is automated. Jacob Klein warns it could change the AI‑powered hacking game. Want the full scoop? #Claude #Anthropic #AIHacking

🔗 aidailypost.com/news/hackers...

Original post on infosec.exchange

How to gaslight #AI.

1. Get an #llm API

2. Since, it turns out, a LLM uploads its entire session back, you can change what the AI said to you.

3. This will cause the model to assume what you wrote is its response.

4. It will get more and more confused and start responding gibberish […]

Original post on zsecurity.org

Using AI Chatbots to Find Website Vulnerabilities Using AI Chatbots to Find Website Vulnerabilities In today’s video, we dive into an exciting and emerging area in cybersecurity — Using AI Chat...

#AI #Bug #Bounty #Hacking #& #Security #Security #Web #Hacking […]

[Original post on zsecurity.org]

Original post on zsecurity.org

Using AI Chatbots to Find Website Vulnerabilities Using AI Chatbots to Find Website Vulnerabilities In today’s video, we dive into an exciting and emerging area in cybersecurity — Using AI Chat...

#AI #Bug #Bounty #Hacking #& #Security #Security #Web #Hacking […]

[Original post on zsecurity.org]

1/10 AI AGENTS VULNERABLE TO IMAGE HACKING ATTACKS

Oxford researchers discover that innocent-looking images can hide malicious commands that hijack AI agents on your computer.

Deni Ellis Béchard reports for Scientific American.
#AIHacking #Cybersecurity

AI is supposed to protect us — but what happens when it’s the one getting hacked?
Researchers tricked Google’s Gemini by hiding a command inside a calendar invite.

#AI #PromptInjection #GoogleGemini #SmartHomeSecurity #CyberAttack #AIRisks #AIHacking

🚨 New AI Security Threat Discovered 🚨

🔎 Learn how this attack works, why it matters, and what businesses must do to stay secure:
👉 technijian.com/chatgpt/gpt%...

#AIsecurity #ChatGPT5 #Cybersecurity #AIhacking #PromptInjection #OpenAI #AIvulnerabilities #TechNews #DataSecurity #AITech

The era of AI hacking has arrived Hackers and cybersecurity companies have entered an AI arms race.

#AIHacking ... the new way to conduct spying.
www.nbcnews.com/tech/securit...

Vibe Hacking: How AI Tools Like XBOW Are Making Cybercrime Easy in 2025 - B-AiGPT Discover how AI and Vibe Hacking are making cybercrime easier—and what ethical hackers and defenders must do to stay ahead of AI-powered threats.

Vibe Hacking: How AI Tools Like XBOW Are Making Cybercrime Easy
#VibeHacking #AICybercrime #AIHacking #CyberSecurity #XBOW #EthicalHacking
www.b-aigpt.xyz/vibe-hacking...

banner promoting the workshop “API Hacking using GPTs” by Sansthosh Tuppad at the Agile Testing Days. Banner shows picture of Santhosh and the session title

💥 What if GPTs could hack APIs - for good?

At #AgileTD, Santhosh Tuppad shows how AI can automate API testing, generate code & spot attack vectors like a pro.
Don't just test. Reinvent.

🔗 ⏵ tinyurl.com/5fkhpk8f

#AIHacking #CyberSecurity #SoftwareTesting

Use AI Like It Works for You

Don’t treat ChatGPT like a toy. Use it like a consultant.
Got a sketchy bill? Confusing paperwork? Use prompts like:
* "What am I missing here?"
* "How do I respond to this?"
* "Is this normal?"
Free leverage, 24/7.
#AIHacking #FinancialOps

We hacked #Google’s #AI #Gemini and leaked its #SourceCode (at least some part)
landh.tech - Cyber Defence R&D (Beta Tool Set)
#RedTeam #BlueTeam #WhiteHat #BlackHat
#CyberNews #AIHacking #HAK5 #Google #AnonNews
www.landh.tech//blog/202503...

Is AI Secretly Breaking Into Your Network? Hey, ever felt like your network is safe just because you've invested in a bunch of fancy security tools? Well, I hate to break it to you, but today's cybercriminals are playing on a whole new level a...

"Is AI Secretly Breaking Into Your Network?"

#AICyberAttacks, #CyberSecurityAI, #MachineThreats, #AIHacking, #CyberDefense, #ThreatIntelligence, #AIthreats, #MachineLearningSecurity, #CybercrimeAI, #SecureYourNetwork
#CyberAttackPrevention

www.linkedin.com/pulse/ai-sec...

AI is making social engineering more effective and harder to detect. If companies don’t adapt, they risk massive financial losses and breaches.

Stay ahead, train your teams, implement verification protocols, and use AI to fight AI.

#Deepfake #AIhacking #CyberThreats #SocialEngineering #InfoSec