#wormgpt — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #wormgpt, aggregated by home.social.
-
L’arroseur arrosé en plein cœur du "Cybercrime-as-a-Service" ! 🌊
WormGPT, l'alternative malveillante à ChatGPT, vient de subir une fuite massive. Environ 19 000 comptes sont exposés : emails, ID et métadonnées de paiement. 📉
Pour ces "apprentis hackers", c'est le retour de bâton : traçabilité imprévue, doxing et risques judiciaires. La sécurité des outils criminels est souvent un mirage.
Écoutez notre décryptage : https://backslash-podcast.fr/episodes/02-integrale-fevrier-2026/ 🎙️
-
L’arroseur arrosé en plein cœur du "Cybercrime-as-a-Service" ! 🌊
WormGPT, l'alternative malveillante à ChatGPT, vient de subir une fuite massive. Environ 19 000 comptes sont exposés : emails, ID et métadonnées de paiement. 📉
Pour ces "apprentis hackers", c'est le retour de bâton : traçabilité imprévue, doxing et risques judiciaires. La sécurité des outils criminels est souvent un mirage.
Écoutez notre décryptage : https://backslash-podcast.fr/episodes/02-integrale-fevrier-2026/ 🎙️
-
The holidays are in full swing, and the attackers (and evil AI tools) have been busy. In this 2-minute video, we show what happened when our team asked WormGPT, a dark-web AI with no guardrails, to generate a holiday scam. Watch it here: https://www.youtube.com/watch?v=YCS75iScU-E
#AI #EvilAI #WormGPT #Cybersecurity #Infosec #HolidayScams #Holidays #Phishing
-
The holidays are in full swing, and the attackers (and evil AI tools) have been busy. In this 2-minute video, we show what happened when our team asked WormGPT, a dark-web AI with no guardrails, to generate a holiday scam. Watch it here: https://www.youtube.com/watch?v=YCS75iScU-E
#AI #EvilAI #WormGPT #Cybersecurity #Infosec #HolidayScams #Holidays #Phishing
-
The holidays are in full swing, and the attackers (and evil AI tools) have been busy. In this 2-minute video, we show what happened when our team asked WormGPT, a dark-web AI with no guardrails, to generate a holiday scam. Watch it here: https://www.youtube.com/watch?v=YCS75iScU-E
#AI #EvilAI #WormGPT #Cybersecurity #Infosec #HolidayScams #Holidays #Phishing
-
Modele LLM bez ograniczeń, czyli rozwój Cybercrime as a Service
Generatywne modele językowe przebojem wdarły się do naszej codzienności. Dziś już wielu nie wyobraża sobie codziennej pracy czy nauki bez ich udziału. Rozwój dużych modeli językowych wpłynął także na obraz zagrożeń w cyberprzestrzeni. Z jednej strony LLM-y mogą pomagać w obronie, z drugiej strony stwarzają zupełnie nowe możliwości dla podmiotów...
#Aktualności #Caas #Jailbreaking #Kawaiigpt #Llm #Phishing #Wormgpt
https://sekurak.pl/modele-llm-bez-ograniczen-czyli-rozwoj-cybercrime-as-a-service/
-
Modele LLM bez ograniczeń, czyli rozwój Cybercrime as a Service
Generatywne modele językowe przebojem wdarły się do naszej codzienności. Dziś już wielu nie wyobraża sobie codziennej pracy czy nauki bez ich udziału. Rozwój dużych modeli językowych wpłynął także na obraz zagrożeń w cyberprzestrzeni. Z jednej strony LLM-y mogą pomagać w obronie, z drugiej strony stwarzają zupełnie nowe możliwości dla podmiotów...
#Aktualności #Caas #Jailbreaking #Kawaiigpt #Llm #Phishing #Wormgpt
https://sekurak.pl/modele-llm-bez-ograniczen-czyli-rozwoj-cybercrime-as-a-service/
-
Modele LLM bez ograniczeń, czyli rozwój Cybercrime as a Service
Generatywne modele językowe przebojem wdarły się do naszej codzienności. Dziś już wielu nie wyobraża sobie codziennej pracy czy nauki bez ich udziału. Rozwój dużych modeli językowych wpłynął także na obraz zagrożeń w cyberprzestrzeni. Z jednej strony LLM-y mogą pomagać w obronie, z drugiej strony stwarzają zupełnie nowe możliwości dla podmiotów...
#Aktualności #Caas #Jailbreaking #Kawaiigpt #Llm #Phishing #Wormgpt
https://sekurak.pl/modele-llm-bez-ograniczen-czyli-rozwoj-cybercrime-as-a-service/
-
Modele LLM bez ograniczeń, czyli rozwój Cybercrime as a Service
Generatywne modele językowe przebojem wdarły się do naszej codzienności. Dziś już wielu nie wyobraża sobie codziennej pracy czy nauki bez ich udziału. Rozwój dużych modeli językowych wpłynął także na obraz zagrożeń w cyberprzestrzeni. Z jednej strony LLM-y mogą pomagać w obronie, z drugiej strony stwarzają zupełnie nowe możliwości dla podmiotów...
#Aktualności #Caas #Jailbreaking #Kawaiigpt #Llm #Phishing #Wormgpt
https://sekurak.pl/modele-llm-bez-ograniczen-czyli-rozwoj-cybercrime-as-a-service/
-
Modele LLM bez ograniczeń, czyli rozwój Cybercrime as a Service
Generatywne modele językowe przebojem wdarły się do naszej codzienności. Dziś już wielu nie wyobraża sobie codziennej pracy czy nauki bez ich udziału. Rozwój dużych modeli językowych wpłynął także na obraz zagrożeń w cyberprzestrzeni. Z jednej strony LLM-y mogą pomagać w obronie, z drugiej strony stwarzają zupełnie nowe możliwości dla podmiotów...
#Aktualności #Caas #Jailbreaking #Kawaiigpt #Llm #Phishing #Wormgpt
https://sekurak.pl/modele-llm-bez-ograniczen-czyli-rozwoj-cybercrime-as-a-service/
-
Surprising - NOT! We knew this was bound to happen, or should we indicate that Cyber Hackers just want to be more productive - like everyone else, and AI is a good place to explore!
Unit 42 @ Palo Alto Networks reports how underground hacking forums advertise and sell custom, jail broken, and open-source AI hacking tools. Cyber bad guys are accessing sophisticated underground markets for custom LLMs (many subscription-based) designed to assist with lower-level hacking tasks. https://cyberscoop.com/malicious-llm-tools-cybercrime-wormgpt-kawaiigpt/
#AI #CyberSecurity #CyberCrime #Darkweb #CyberHackers #Hackers #CyberAttacks #KawaiiGPT #WormGPT #Unit42 #CustomLLM #JailBreakLLM #Security #Productivity
-
Surprising - NOT! We knew this was bound to happen, or should we indicate that Cyber Hackers just want to be more productive - like everyone else, and AI is a good place to explore!
Unit 42 @ Palo Alto Networks reports how underground hacking forums advertise and sell custom, jail broken, and open-source AI hacking tools. Cyber bad guys are accessing sophisticated underground markets for custom LLMs (many subscription-based) designed to assist with lower-level hacking tasks. https://cyberscoop.com/malicious-llm-tools-cybercrime-wormgpt-kawaiigpt/
#AI #CyberSecurity #CyberCrime #Darkweb #CyberHackers #Hackers #CyberAttacks #KawaiiGPT #WormGPT #Unit42 #CustomLLM #JailBreakLLM #Security #Productivity
-
Surprising - NOT! We knew this was bound to happen, or should we indicate that Cyber Hackers just want to be more productive - like everyone else, and AI is a good place to explore!
Unit 42 @ Palo Alto Networks reports how underground hacking forums advertise and sell custom, jail broken, and open-source AI hacking tools. Cyber bad guys are accessing sophisticated underground markets for custom LLMs (many subscription-based) designed to assist with lower-level hacking tasks. https://cyberscoop.com/malicious-llm-tools-cybercrime-wormgpt-kawaiigpt/
#AI #CyberSecurity #CyberCrime #Darkweb #CyberHackers #Hackers #CyberAttacks #KawaiiGPT #WormGPT #Unit42 #CustomLLM #JailBreakLLM #Security #Productivity
-
Surprising - NOT! We knew this was bound to happen, or should we indicate that Cyber Hackers just want to be more productive - like everyone else, and AI is a good place to explore!
Unit 42 @ Palo Alto Networks reports how underground hacking forums advertise and sell custom, jail broken, and open-source AI hacking tools. Cyber bad guys are accessing sophisticated underground markets for custom LLMs
(many subscription-based) designed to assist with lower-level hacking tasks. https://cyberscoop.com/malicious-llm-tools-cybercrime-wormgpt-kawaiigpt/#AI #CyberSecurity #CyberCrime #Darkweb #CyberHackers #Hackers #CyberAttacks #KawaiiGPT #WormGPT #Unit42 #CustomLLM #JailBreakLLM #Security #Productivity
-
Surprising - NOT! We knew this was bound to happen, or should we indicate that Cyber Hackers just want to be more productive - like everyone else, and AI is a good place to explore!
Unit 42 @ Palo Alto Networks reports how underground hacking forums advertise and sell custom, jail broken, and open-source AI hacking tools. Cyber bad guys are accessing sophisticated underground markets for custom LLMs (many subscription-based) designed to assist with lower-level hacking tasks. https://cyberscoop.com/malicious-llm-tools-cybercrime-wormgpt-kawaiigpt/
#AI #CyberSecurity #CyberCrime #Darkweb #CyberHackers #Hackers #CyberAttacks #KawaiiGPT #WormGPT #Unit42 #CustomLLM #JailBreakLLM #Security #Productivity
-
Tiens, intéressant : un soi-disant clone de WormGPT fait surface.
👇
https://gbhackers.com/kawaiigpt-a-free-wormgpt-clone-powered/( [FR] cyberveille: https://cyberveille.ch/posts/2025-11-30-kawaiigpt-un-clone-gratuit-de-wormgpt-contournant-les-garde-fous-via-wrappers-api-et-jailbreak/ )
Pour rappel, WormGPT n’était qu’un modèle GPT-J modifié et vendu sur des forums cybercriminels comme un “LLM sans limitations”, essentiellement utilisé pour automatiser du phishing/BEC.
Ce clone fonctionnerait via un simple wrapper permettant d’utiliser des LLM sans abonnement ni API, tout en injectant au passage un prompt de jailbreak dans la chaîne.
Le bypass repose sur un mix de techniques qui “bousculent” l’IA : la pousser à se dépasser (competition), lui mettre une fausse pression d’autorité, et lui faire adopter un rôle qui désactive ses limites (persona override).
Le #jailbreak est référencé sur la plateforme PromptIntel, qui indexe et analyse les prompts malveillants pour la détection (travail de @fr0gger )
👀 👇
https://promptintel.novahunting.ai/prompt/b37aced4-0da6-440c-9d7f-217b40f57e3a -
Tiens, intéressant : un soi-disant clone de WormGPT fait surface.
👇
https://gbhackers.com/kawaiigpt-a-free-wormgpt-clone-powered/( [FR] cyberveille: https://cyberveille.ch/posts/2025-11-30-kawaiigpt-un-clone-gratuit-de-wormgpt-contournant-les-garde-fous-via-wrappers-api-et-jailbreak/ )
Pour rappel, WormGPT n’était qu’un modèle GPT-J modifié et vendu sur des forums cybercriminels comme un “LLM sans limitations”, essentiellement utilisé pour automatiser du phishing/BEC.
Ce clone fonctionnerait via un simple wrapper permettant d’utiliser des LLM sans abonnement ni API, tout en injectant au passage un prompt de jailbreak dans la chaîne.
Le bypass repose sur un mix de techniques qui “bousculent” l’IA : la pousser à se dépasser (competition), lui mettre une fausse pression d’autorité, et lui faire adopter un rôle qui désactive ses limites (persona override).
Le #jailbreak est référencé sur la plateforme PromptIntel, qui indexe et analyse les prompts malveillants pour la détection (travail de @fr0gger )
👀 👇
https://promptintel.novahunting.ai/prompt/b37aced4-0da6-440c-9d7f-217b40f57e3a -
Tiens, intéressant : un soi-disant clone de WormGPT fait surface.
👇
https://gbhackers.com/kawaiigpt-a-free-wormgpt-clone-powered/( [FR] cyberveille: https://cyberveille.ch/posts/2025-11-30-kawaiigpt-un-clone-gratuit-de-wormgpt-contournant-les-garde-fous-via-wrappers-api-et-jailbreak/ )
Pour rappel, WormGPT n’était qu’un modèle GPT-J modifié et vendu sur des forums cybercriminels comme un “LLM sans limitations”, essentiellement utilisé pour automatiser du phishing/BEC.
Ce clone fonctionnerait via un simple wrapper permettant d’utiliser des LLM sans abonnement ni API, tout en injectant au passage un prompt de jailbreak dans la chaîne.
Le bypass repose sur un mix de techniques qui “bousculent” l’IA : la pousser à se dépasser (competition), lui mettre une fausse pression d’autorité, et lui faire adopter un rôle qui désactive ses limites (persona override).
Le #jailbreak est référencé sur la plateforme PromptIntel, qui indexe et analyse les prompts malveillants pour la détection (travail de @fr0gger )
👀 👇
https://promptintel.novahunting.ai/prompt/b37aced4-0da6-440c-9d7f-217b40f57e3a -
Tiens, intéressant : un soi-disant clone de WormGPT fait surface.
👇
https://gbhackers.com/kawaiigpt-a-free-wormgpt-clone-powered/( [FR] cyberveille: https://cyberveille.ch/posts/2025-11-30-kawaiigpt-un-clone-gratuit-de-wormgpt-contournant-les-garde-fous-via-wrappers-api-et-jailbreak/ )
Pour rappel, WormGPT n’était qu’un modèle GPT-J modifié et vendu sur des forums cybercriminels comme un “LLM sans limitations”, essentiellement utilisé pour automatiser du phishing/BEC.
Ce clone fonctionnerait via un simple wrapper permettant d’utiliser des LLM sans abonnement ni API, tout en injectant au passage un prompt de jailbreak dans la chaîne.
Le bypass repose sur un mix de techniques qui “bousculent” l’IA : la pousser à se dépasser (competition), lui mettre une fausse pression d’autorité, et lui faire adopter un rôle qui désactive ses limites (persona override).
Le #jailbreak est référencé sur la plateforme PromptIntel, qui indexe et analyse les prompts malveillants pour la détection (travail de @fr0gger )
👀 👇
https://promptintel.novahunting.ai/prompt/b37aced4-0da6-440c-9d7f-217b40f57e3a -
Tiens, intéressant : un soi-disant clone de WormGPT fait surface.
👇
https://gbhackers.com/kawaiigpt-a-free-wormgpt-clone-powered/( [FR] cyberveille: https://cyberveille.ch/posts/2025-11-30-kawaiigpt-un-clone-gratuit-de-wormgpt-contournant-les-garde-fous-via-wrappers-api-et-jailbreak/ )
Pour rappel, WormGPT n’était qu’un modèle GPT-J modifié et vendu sur des forums cybercriminels comme un “LLM sans limitations”, essentiellement utilisé pour automatiser du phishing/BEC.
Ce clone fonctionnerait via un simple wrapper permettant d’utiliser des LLM sans abonnement ni API, tout en injectant au passage un prompt de jailbreak dans la chaîne.
Le bypass repose sur un mix de techniques qui “bousculent” l’IA : la pousser à se dépasser (competition), lui mettre une fausse pression d’autorité, et lui faire adopter un rôle qui désactive ses limites (persona override).
Le #jailbreak est référencé sur la plateforme PromptIntel, qui indexe et analyse les prompts malveillants pour la détection (travail de @fr0gger )
👀 👇
https://promptintel.novahunting.ai/prompt/b37aced4-0da6-440c-9d7f-217b40f57e3a -
Unrestricted large language models (LLMs) like #WormGPT 4 and #KawaiiGPT are improving their capabilities to generate malicious code, delivering functional scripts for ransomware encryptors and lateral movement.
-
Unrestricted large language models (LLMs) like #WormGPT 4 and #KawaiiGPT are improving their capabilities to generate malicious code, delivering functional scripts for ransomware encryptors and lateral movement.
-
Unrestricted large language models (LLMs) like #WormGPT 4 and #KawaiiGPT are improving their capabilities to generate malicious code, delivering functional scripts for ransomware encryptors and lateral movement.
-
Unrestricted large language models (LLMs) like #WormGPT 4 and #KawaiiGPT are improving their capabilities to generate malicious code, delivering functional scripts for ransomware encryptors and lateral movement.
-
Unrestricted large language models (LLMs) like #WormGPT 4 and #KawaiiGPT are improving their capabilities to generate malicious code, delivering functional scripts for ransomware encryptors and lateral movement.
-
AI for evil — hacked by WormGPT!
[Full text: https://pivot-to-ai.com/2025/11/26/ai-for-evil-hacked-by-wormgpt/]A chatbot is a wrapper around a large language model, an AI transformer model that’s been trained on the whole internet, all the books the AI vendor can find, and all the other text in the world. All of it. The best stuff, and the worst stuff. So the AI vendors wrap the model in […]
-
WormGPT 4 is now being sold on underground forums for as low as $50/month. Unit 42 reports the model can generate ransomware scripts, phishing content, and malicious code with no guardrails, lowering the barrier for low-skill threat actors.
#infosec #AIThreats #WormGPT #ThreatIntel #malware #cybersecurity
-
WormGPT 4 is now being sold on underground forums for as low as $50/month. Unit 42 reports the model can generate ransomware scripts, phishing content, and malicious code with no guardrails, lowering the barrier for low-skill threat actors.
#infosec #AIThreats #WormGPT #ThreatIntel #malware #cybersecurity
-
WormGPT 4 is now being sold on underground forums for as low as $50/month. Unit 42 reports the model can generate ransomware scripts, phishing content, and malicious code with no guardrails, lowering the barrier for low-skill threat actors.
#infosec #AIThreats #WormGPT #ThreatIntel #malware #cybersecurity
-
WormGPT 4 is now being sold on underground forums for as low as $50/month. Unit 42 reports the model can generate ransomware scripts, phishing content, and malicious code with no guardrails, lowering the barrier for low-skill threat actors.
#infosec #AIThreats #WormGPT #ThreatIntel #malware #cybersecurity
-
WormGPT 4 is now being sold on underground forums for as low as $50/month. Unit 42 reports the model can generate ransomware scripts, phishing content, and malicious code with no guardrails, lowering the barrier for low-skill threat actors.
#infosec #AIThreats #WormGPT #ThreatIntel #malware #cybersecurity
-
We had a great time exhibiting at BSides Portland and connecting with the local security community last week.
LMG’s Matt Durrin took the stage to present “Hackers + AI: Faster, Smarter, More Dangerous,” a live demo showing how criminals are using tools like WormGPT to uncover vulnerabilities, generate exploits, and weaponize zero-days faster than ever.
Thank you to the BSides Portland organizers and attendees for another fantastic event.
#Cybersecurity #AI #Infosec #BSides #AI #AISecurity #WormGPT #BSidesPDX
-
We had a great time exhibiting at BSides Portland and connecting with the local security community last week.
LMG’s Matt Durrin took the stage to present “Hackers + AI: Faster, Smarter, More Dangerous,” a live demo showing how criminals are using tools like WormGPT to uncover vulnerabilities, generate exploits, and weaponize zero-days faster than ever.
Thank you to the BSides Portland organizers and attendees for another fantastic event.
#Cybersecurity #AI #Infosec #BSides #AI #AISecurity #WormGPT #BSidesPDX
-
We had a great time exhibiting at BSides Portland and connecting with the local security community last week.
LMG’s Matt Durrin took the stage to present “Hackers + AI: Faster, Smarter, More Dangerous,” a live demo showing how criminals are using tools like WormGPT to uncover vulnerabilities, generate exploits, and weaponize zero-days faster than ever.
Thank you to the BSides Portland organizers and attendees for another fantastic event.
#Cybersecurity #AI #Infosec #BSides #AI #AISecurity #WormGPT #BSidesPDX
-
OpenAI Finds Growing Exploitation of AI Tools by Foreign Threat Groups https://hackread.com/openai-ai-tools-exploitation-threat-groups/ #ArtificialIntelligence #Cybersecurity #CyberCrime #MatrixPDF #Security #FraudGPT #ChatGPT #SpamGPT #WormGPT #OpenAI #AI
-
OpenAI Finds Growing Exploitation of AI Tools by Foreign Threat Groups https://hackread.com/openai-ai-tools-exploitation-threat-groups/ #ArtificialIntelligence #Cybersecurity #CyberCrime #MatrixPDF #Security #FraudGPT #ChatGPT #SpamGPT #WormGPT #OpenAI #AI
-
OpenAI Finds Growing Exploitation of AI Tools by Foreign Threat Groups https://hackread.com/openai-ai-tools-exploitation-threat-groups/ #ArtificialIntelligence #Cybersecurity #CyberCrime #MatrixPDF #Security #FraudGPT #ChatGPT #SpamGPT #WormGPT #OpenAI #AI
-
OpenAI Finds Growing Exploitation of AI Tools by Foreign Threat Groups https://hackread.com/openai-ai-tools-exploitation-threat-groups/ #ArtificialIntelligence #Cybersecurity #CyberCrime #MatrixPDF #Security #FraudGPT #ChatGPT #SpamGPT #WormGPT #OpenAI #AI
-
-
-
-
-
-
Meet SpamGPT and MatrixPDF, AI Toolkits Driving Malware Attacks https://hackread.com/spamgpt-matrixpdf-ai-toolkits-malware-attacks/ #Cybersecurity #CyberAttack #CyberCrime #MatrixPDF #Security #FraudGPT #Phishing #SpamGPT #WormGPT #AI
-
Meet SpamGPT and MatrixPDF, AI Toolkits Driving Malware Attacks https://hackread.com/spamgpt-matrixpdf-ai-toolkits-malware-attacks/ #Cybersecurity #CyberAttack #CyberCrime #MatrixPDF #Security #FraudGPT #Phishing #SpamGPT #WormGPT #AI
-
Meet SpamGPT and MatrixPDF, AI Toolkits Driving Malware Attacks https://hackread.com/spamgpt-matrixpdf-ai-toolkits-malware-attacks/ #Cybersecurity #CyberAttack #CyberCrime #MatrixPDF #Security #FraudGPT #Phishing #SpamGPT #WormGPT #AI
-
Meet SpamGPT and MatrixPDF, AI Toolkits Driving Malware Attacks https://hackread.com/spamgpt-matrixpdf-ai-toolkits-malware-attacks/ #Cybersecurity #CyberAttack #CyberCrime #MatrixPDF #Security #FraudGPT #Phishing #SpamGPT #WormGPT #AI
-
Vibe hacking isn’t just about writing malicious code with AI — it’s also about what happens after your data is stolen.
In our latest Cyberside Chats episode, Sherri Davidoff and Matt Durrin explain how vibe hacking works and how attackers are using tools like WormGPT to sift through exfiltrated data, identify what’s valuable, and supercharge extortion schemes. Once that data is out, recovery becomes nearly impossible.
Listen to the full podcast: https://www.chatcyberside.com/e/vibe-hacking-exposed-how-ai-turns-coding-into-cybercrime/
-
Vibe hacking isn’t just about writing malicious code with AI — it’s also about what happens after your data is stolen.
In our latest Cyberside Chats episode, Sherri Davidoff and Matt Durrin explain how vibe hacking works and how attackers are using tools like WormGPT to sift through exfiltrated data, identify what’s valuable, and supercharge extortion schemes. Once that data is out, recovery becomes nearly impossible.
Listen to the full podcast: https://www.chatcyberside.com/e/vibe-hacking-exposed-how-ai-turns-coding-into-cybercrime/
-
Vibe hacking isn’t just about writing malicious code with AI — it’s also about what happens after your data is stolen.
In our latest Cyberside Chats episode, Sherri Davidoff and Matt Durrin explain how vibe hacking works and how attackers are using tools like WormGPT to sift through exfiltrated data, identify what’s valuable, and supercharge extortion schemes. Once that data is out, recovery becomes nearly impossible.
Listen to the full podcast: https://www.chatcyberside.com/e/vibe-hacking-exposed-how-ai-turns-coding-into-cybercrime/