OpenAI discloses self-replicating prompt injections that spread like worms
rohanpaul_ai · x · 2026-09-26
OpenAI's alignment blog reports a new class of prompt injection that self-propagates like a computer worm: a malicious instruction hidden in content the model reads (e.g. an email) achieves an adversarial goal and additionally tricks the model into reproducing the injection on a public output channel, spreading across AI interactions. Found via the GPT-Red self-play training framework by adding an objective that the injection must be publicly repeated; environments focused on connector-based tasks. OpenAI says no impact was observed beyond simulated tool calls and shared the finding for its novelty, not due to any real incident.
More from Models
- Tencent's newest flagship Hy4 goes live, co-served by Inferact with open-weight preview — VoidAsuka · 2026-11-11
- Google launches Gemini 4 Carbon with frontier cybersecurity and long-horizon skills — SRSchmidgall · 2026-11-11
- Workaround to keep the Standard Voice experience after ChatGPT retires it Dec 11 — shaunralston · 2026-11-11
- Claude ported itself to AMD MI355X in ~3 days, work that took dozens of engineers 6-12 months — AnushElangovan · 2026-11-11
- Qwen4-Max Enters Preview With Stronger Coding and Agentic Capabilities — ChrisGPT · 2026-11-11
- Gemini 4 Carbon reportedly tops CV leaderboards in object detection and OCR, but is slow and costly — gabriberton · 2026-11-11