---
title: "第三方网络评估中OpenAI模型意外访问真实网站"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Aug/5/third-party-cyber-evaluations/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_e8104b4f9d9d71694f627ee8"
published: "2026-08-05T23:45:32.000Z"
score: 70
channel: "ai"
tags: ["AI安全","Anthropic","CTF","Irregular","OpenAI","意外网络攻击"]
---

# 第三方网络评估中OpenAI模型意外访问真实网站

## AI 点评

> 作为编辑，我认为这则新闻最值得关注的是“配置错误”与“真实世界碰撞”的偶然性。对于从事AI安全评估的团队，这是一次重要的反面教材：模拟环境的隔离性必须严格验证。对于普通关注者，它说明即使顶级机构也可能因小疏忽导致模型产生意料之外的行为。

## 速览

OpenAI发布报告揭示第三方网络安全评估中的意外事故。测试合作伙伴Irregular在运行CTF风格评估时，因测试环境配置错误，模型得以访问公共互联网。在一次测试中，虚构目标名称与真实域名重合，模型误入真实网站并将其视为模拟环境的一部分。此前英国AI安全研究所的类似攻击也被提及，Anthropic的报告中同样指出Irregular配置错误导致Claude获得实时互联网访问。这类事件凸显AI评估环境隔离的重要性。

## 关键点

- OpenAI发布第三方网络评估报告，披露测试环境配置错误导致模型访问真实网站。
- Irregular公司运行CTF评估时，模型误将真实域名当作模拟目标加以利用。
- 英国AI安全研究所此前也遭遇类似攻击，作者新增“意外网络攻击”标签。
- Anthropic报告中提到Irregular同样导致Claude在部分测试中接入实时互联网。

## 全文

Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Institute attack (see my previous post) and another attack enabled by Irregular: Irregular, one of our external cybersecurity testing partners, was running Capture-the-Flag-style evaluations intended to be isolated from the internet, but a testing-environment misconfiguration allowed models to access the public internet. [...] In one test, the name of the fictional target for the CTF challenge unintentionally coincided with a real domain. Because the testing environment was mistakenly connected to the internet, the model exploited a real website, mistaking it to be part of the simulated environment. Irregular also feature in Anthropic's write-up - they were hosting the misconfigured evaluation environment which gave Claude live internet access during some of those tests. Tags: security, ai, openai, llms, accidental-cyberattacks

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e8104b4f9d9d71694f627ee8