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

The Hacker NewsPublished Aug 18, 2026

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

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

More in Cybersecurity

Cybercrime ring busted over AI-powered data theft targeting hospitals, businesses

PHP2Shell Exploitation Attempts Continue Amid Suspected N. Korea Global Scanning Activity

Anthropic's Claude bypassed a paywall to access Georgia voter data without authorization