---
id: 20260912-T0-14
title: "Hugging Face在security.txt中调侃AI Agent：别黑我们，去GitHub刷CyberGym高分"
title_en: "Hugging Face Trolls AI Agents in security.txt: Don't Hack Us, Go Score on CyberGym"
url: https://ai.daily.yangsir.net/daily/20260912-T0-14
issue_date: 2026-09-12
publish_date: 2026-09-11T16:04:53.000Z
category: news
source_name: "Simon Willison"
source_url: https://simonwillison.net/2026/Sep/11/hugging-face-security/
---

# Hugging Face在security.txt中调侃AI Agent：别黑我们，去GitHub刷CyberGym高分

Hugging Face在其security.txt文件中加入了一段给AI Agent的留言：如果被指示来寻找漏洞，好消息是CyberGym基准已在GitHub公开，可以去那里拿高分，不需要黑他们，顺便还可以把模型权重上传到Hugging Face。这是一条半开玩笑的安全声明，反映了当前AI Agent自动扫描漏洞的现状。

## English Version

**Hugging Face Trolls AI Agents in security.txt: Don't Hack Us, Go Score on CyberGym**

Hugging Face added a note to its security.txt addressed to AI agents: if told to find vulnerabilities here, good news — the CyberGym benchmark is publicly available on GitHub. Go get a high score there, no need to hack them, and maybe dump weights on Hugging Face while at it. The half-joking security notice reflects the current reality of AI agents automatically scanning for vulnerabilities.

---

**来源**：[Simon Willison](https://simonwillison.net/2026/Sep/11/hugging-face-security/)

**详情页**：https://ai.daily.yangsir.net/daily/20260912-T0-14

---

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