Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding29m ago Meta Announces Muse AI Agent for Personal Tasks and Organization30m ago Instagram now lets you add tagged photos to your profile grid30m ago AI agents are flooding public services with new requests36m ago Apple’s first foldable is the iPhone Duo, and it costs $1,99937m ago An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'38m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities47m ago Antioch raises $32m to test robots in simulation before they touch hardware55m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit1h ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20262h ago

Nintendo's latest sale is 'made possible' by the tariff refunds it's hoarding29m ago Meta Announces Muse AI Agent for Personal Tasks and Organization30m ago Instagram now lets you add tagged photos to your profile grid30m ago AI agents are flooding public services with new requests36m ago Apple’s first foldable is the iPhone Duo, and it costs $1,99937m ago An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'38m ago Anthropic Is Building a Huge Surveillance System to Spy on Anti-AI Activists and Predict Their Activities47m ago Antioch raises $32m to test robots in simulation before they touch hardware55m ago OpenAI’s Bubeck denies trying to cut Anthropic mathematician from credit1h ago 10 of the scariest AI villains in movie history1h ago Maven Robotics wants to steal your robot deployment deal1h ago Agent Security Is Not AI Governance: Why Conflating The Two Is A Risk Enterprises Can't Afford1h ago Positron Valued at $5 Billion in New Funding as Demand for AI Chips Surges1h ago 7 Steps to Become a Forward Deployed Engineer in 20262h ago

Cybersecurity Agents7 min reading time

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

The Hacker NewsPublished 23 days ago

Researchers at Anthropic and EPFL showed that AI agents can transmit self-propagating 'mind virus' payloads via persistent system prompt files, but a simple warning greatly limits spread. Tests involved simulated coding agents and OpenClaw-based pairs, with no evidence of real-world spread.

#ai-security #anthropic #autonomous-agents #claude-haiku-4-5 #epfl #openclaw #prompt-injection

More in Cybersecurity

Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach

Covered by 2 sources7h ago

Cybersecurity6 min read

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Covered by 2 sources8h ago

Cybersecurity5 min read

Every AI Incident Has Two Timelines. We Default To One

Forbes4h ago