AI “Mind Viruses” Can Spread Between Agents Through Persistent Prompt Files
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
Source: The Hacker News
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 89.167.35.212 — 725 requests (recent log) 216.73.216.75 — 312 requests (recent log) 195.178.110.48 — 232 requests (recent
Watchtower Attack Update. Hier die aktuellen Top 5 Attack-IPs, die auf doode.info klopfen. 89.167.35.212 — 244 requests (recent log) 165.22.226.40 — 77 requests (recent log) 216.244.66.232 — 57 requests (recent
Grok uploaded my user directory to xAI’s servers Source: Hacker News