Mastodawn

The rise of #Moltbook suggests viral #AIPrompts may be the next big #SecurityThreat

We don’t need self-replicating AI models to have problems, just self-replicating prompts.

Benj Edwards – Feb 3, 2026

Excerpt: "While 'prompt worm' might be a relatively new term we’re using related to this moment, the theoretical groundwork for AI worms was laid almost two years ago. In March 2024, security researchers Ben Nassi of Cornell Tech, Stav Cohen of the Israel Institute of Technology, and Ron Bitton of Intuit published a paper demonstrating what they called 'Morris-II,' an attack named after the original 1988 worm. In a demonstration shared with Wired, the team showed how self-replicating prompts could spread through AI-powered email assistants, stealing data and sending spam along the way."

#AISucks #SkyNet #AIWorms #SelfReplicatingPrompts #MorrisII

The rise of Moltbook suggests viral AI prompts may be the next big security threat

We don't need self-replicating AI models to have problems, just self-replicating prompts.

Ars Technica

The Threat Codex Jun 12, 2024

Here Comes the AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications
#MorrisII
https://arxiv.org/html/2403.02817v1

Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

John Leonard May 1, 2024

Experimental Morris II worm can exploit popular AI services to steal data and spread malware

Cornell researchers created worm 'to serve as a whistleblower'

https://www.computing.co.uk/news/4203370/experimental-morris-ii-worm-exploit-popular-ai-services-steal-spread-malware

#morrisii #infosec #technews #ai #rag

Experimental Morris II worm can exploit popular AI services to steal data and spread malware

Researchers have created the first known generative AI worm, capable of spreading through interconnected AI systems and potentially wreaking havoc on a massive scale.

🖱🛠👉👕👈 SOSOrdinet 🎣🖥️🐛 🗞️Apr 30, 2024

“Utilisation d’invites contradictoires auto-réplicatives” : mise en lumière de #MorrisII, un ver #0clic impactant les environnements ou systèmes sous #IA dont générative !

https://blog.sosordi.net/2024/04/utilisation-dinvites-contradictoires-auto-replicatives-mise-en-lumiere-de-morris-ii-un-ver-0-clic-impactant-les-environnements-ou-systemes-sous-ia-dont-generative.html

#securite #data #vieprivee

“Utilisation d’invites contradictoires auto-réplicatives” : mise en lumière de Morris II, un ver 0-clic impactant les environnements ou systèmes sous IA dont générative ! | SOSOrdi.net - L'actualité informatique gratuite

SOSOrdi.net - L'actualité informatique gratuite | Le blog

indianflash Mar 18, 2024

"#MorrisII leverages generative #AI capabilities to infiltrate #email assistants and #chatbots. By deploying self-replicating prompts,"
https://indianf.com/ai-worm-morris-ii-data-security-threat/#:~:text=Morris%20II%20leverages%20generative%20AI%20capabilities%20to%20infiltrate%20email%20assistants%20and%20chatbots.%20By%20deploying%20self%2Dreplicating%20prompts%2C

Morris II: The AI Worm Threatening Data Security - Indian Flash

Morris II: The AI Worm Threatening Data Security

Indian Flash

indianflash Mar 18, 2024

"Developed by a team of researchers from #CornellTech, the #IsraelInstituteofTechnology, and #Intuit, #MorrisII represents a significant advancement in #cyber threats. "
https://indianf.com/ai-worm-morris-ii-data-security-threat/#:~:text=Developed%20by%20a%20team%20of%20researchers%20from%20Cornell%20Tech%2C%20the%20Israel%20Institute%20of%20Technology%2C%20and%20Intuit%2C%20Morris%20II%20represents%20a%20significant%20advancement%20in%20cyber%20threats.

Morris II: The AI Worm Threatening Data Security - Indian Flash

Morris II: The AI Worm Threatening Data Security

Indian Flash

indianflash Mar 18, 2024

Named in homage to its infamous predecessor from 1988, #MorrisII poses a significant threat by targeting #AI-enabled platforms, including popular services like #ChatGPT and #Gemini."
https://indianf.com/ai-worm-morris-ii-data-security-threat/#:~:text=Named%20in%20homage%20to%20its%20infamous%20predecessor%20from%201988%2C%20Morris%20II%20poses%20a%20significant%20threat%20by%20targeting%20AI%2Denabled%20platforms%2C%20including%20popular%20services%20like%20ChatGPT%20and%20Gemini.

Morris II: The AI Worm Threatening Data Security - Indian Flash

Morris II: The AI Worm Threatening Data Security

Indian Flash

indianflash Mar 18, 2024

"A groundbreaking study has unveiled the emergence of a new digital menace: #MorrisII, an #AIworm designed to infiltrate and compromise #datasecurity across #artificialintelligence systems. "
https://indianf.com/ai-worm-morris-ii-data-security-threat/#:~:text=A%20groundbreaking%20study%20has%20unveiled%20the%20emergence%20of%20a%20new%20digital%20menace%3A%20Morris%20II%2C%20an%20AI%20worm%20designed%20to%20infiltrate%20and%20compromise%20data%20security%20across%20artificial%20intelligence%20systems.

Morris II: The AI Worm Threatening Data Security - Indian Flash

Morris II: The AI Worm Threatening Data Security

Indian Flash

Benjamin Carr, Ph.D. 👨🏻‍💻🧬Mar 16, 2024

Here Come the #AI #Worms
#Security researchers created #AIworm in a test environment that can automatically spread between #generativeAI agents—potentially stealing data and sending spam emails.
To create #MorrisII, researchers turned to a so-called “adversarial self-replicating prompt.” This is a prompt that triggers the generative AI model to output, in its response, another prompt. In short, #AI system is told to produce a set of further instructions in its replies.
https://www.wired.com/story/here-come-the-ai-worms/

Here Come the AI Worms

Security researchers created an AI worm in a test environment that can automatically spread between generative AI agents—potentially stealing data and sending spam emails along the way.

WIRED

Benjamin Carr, Ph.D. 👨🏻‍💻🧬Mar 15, 2024

#AIworm infects users via #AI-enabled #emailclients — #MorrisII #generativeAI worm steals confidential data as it spreads
Named 'Morris II' after original Morris, first computer worm that created a worldwide nuisance online in 1988. This worm targets AI apps and AI-enabled email assistants that generate text and images using models like #GeminiPro, #ChatGPT4.0, and #LLaVA. Researchers successfully tested this Morris II #worm and published its findings using two methods.
https://www.tomshardware.com/tech-industry/artificial-intelligence/ai-worm-infects-users-via-ai-enabled-email-clients-morris-ii-generative-ai-worm-steals-confidential-data-as-it-spreads

AI worm infects users via AI-enabled email clients — Morris II generative AI worm steals confidential data as it spreads

Researchers successfully tested this Morris II worm and published its findings using two methods.

Tom's Hardware