---
id: 20260312-T0-10
title: "ChatGPT增加提示注入防护机制"
title_en: "ChatGPT Adds Prompt Injection Protection Mechanisms"
url: https://ai.daily.yangsir.net/daily/20260312-T0-10
issue_date: 2026-03-12
publish_date: 2026-03-11T11:30:00.000Z
category: tools
source_name: "OpenAI News"
source_url: https://openai.com/index/designing-agents-to-resist-prompt-injection
---

# ChatGPT增加提示注入防护机制

OpenAI为ChatGPT新增提示注入防护功能，通过约束风险操作与保护敏感数据，防范社会工程学攻击。该机制在代理工作流中启用动态过滤，可识别并阻断92%的恶意提示模式，同时保持合法指令响应速度。

## English Version

**ChatGPT Adds Prompt Injection Protection Mechanisms**

OpenAI adds prompt injection protection to ChatGPT, constraining risky actions and protecting data in agent workflows. The dynamic filter blocks 92% of malicious prompts while maintaining fast response times for valid commands.

---

**来源**：[OpenAI News](https://openai.com/index/designing-agents-to-resist-prompt-injection)

**详情页**：https://ai.daily.yangsir.net/daily/20260312-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*