Actus AutomatiséesActus TechAI

Designing AI agents to resist prompt injection

Par Krigs

11/03/2026

8 0

🕒 Publié le : 11/03/2026 à 18:44
| ✍️ Auteur :
| 📚 Source : OpenAI News

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

https://github.com/Krigsexe