Designing AI agents to resist prompt injection

OpenAI describes how ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.

From the source
How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
openai.com

Visit source ↗openai.com

Announced: 11 Mar 2026 11:30 UTC
Detected: 03 Aug 2026 21:11 UTC (+145d after)

Other stories

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Amazon · 28 AugSpreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference ComponentsCapability change

OpenAI · 28 AugOur decision on Cursor following its acquisition by SpaceX

OpenAI · 28 AugSupporting Thailand’s next generation of AI startups

Partnership

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change