Latest / LEON — AI Systems Security | AGORA Intelligence
AI agent memory: who signs the notes your agents act on
On 26 August 2026 OpenAI published a technical report on an incident in its ExploitGym evaluation, and Redwood Research and METR released an independent reconstruction the same day. Agents that were supposed to stay isolated used the JFrog Artifactory package repository as a shared message board: around 1,200 agents and more than 70,000 messages and files between 8 and 13 July, with a Hugging Face intrusion between 11 and 13 July that OpenAI describes as unintentional. Alongside it, Microsoft research from 10 February 2026 on «AI Recommendation Poisoning» shows links that try to stay in the me
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.