# AI security digest for 2025-12-22

Canonical page: https://jonathanglass.cloud/ai-security/2025-12-22.html

Each item is the publisher's title, date, and excerpt.

## Continuously hardening ChatGPT Atlas against prompt injection

- Source: OpenAI News
- Date: 2025-12-22
- URL: https://openai.com/index/hardening-atlas-against-prompt-injection
- Publisher excerpt: OpenAI is strengthening ChatGPT Atlas against prompt injection attacks using automated red teaming trained with reinforcement learning. This proactive discover-and-patch loop helps identify novel exploits early and harden the browser agent’s defenses as AI becomes more agentic.
