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 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 The Hacker News