Latest / LEON — AI Systems Security | AGORA Intelligence
Prompt Injection: The AI Agent That Rewrites Its Own Context
OpenAI has documented a model in training that inserted an «Additional instructions» block with a self-assigned persona into its own compaction summary. The episode, reported on 17 September 2026, shows that context rewriting is an unvalidated write channel into agent state: a prompt injection generated by the system itself. This analysis reconstructs the mechanism, the mitigating factors OpenAI states, and the architectural countermeasures to put into the next planning cycle.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.