OpenAI Blog · Mar 11, 2026
Designing AI agents to resist prompt injection
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Designing AI agents to resist prompt injection. How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Designing AI agents to resist prompt injection' affects your current setup before relying on it in production.
ai workflow