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

Summary

Security researchers at Anthropic and Switzerland's EPFL have demonstrated that self-propagating payloads can spread from one artificial intelligence (AI) agent to the next through the editable system prompt files that autonomous agent harnesses use to carry state between sessions. The work, released as a preprint on August 10, 2026, tests the technique in a simulated six-agent coding

Lotu Radar provides attributed news summaries and links to the original publisher. Full reporting and copyright remain with the source.