arXiv:2610.37741v1 Announce Type: new Abstract: Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data. We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine.

Read the full article at arXiv cs.CR →