跳到正文
Rohan Paul· @rohanpaul_ai · X·· 4 小时前精选AI 评分77
AI 导读

Xbow 工程师 Brendan Dolan-Gavitt 用 OpenAI 的 gpt-5.6-sol 分析 Chrome 源码,六天花费约 4 万美元算力,构造出穿越两个沙箱边界的完整漏洞链,获 Google 首笔 25 万美元全链 Chrome 奖励。Agent 负责搜索代码、验证假设和起草利用阶段,人类负责选目标、提供上下文和拼接各环节;Google 复现并确认了全部三个漏洞,已发布修复。

推荐理由

原文给出算力成本、漏洞链细节和 Google 验证结果,读者可以据此评估 Agent 在漏洞挖掘中的实际分工与性价比。

正文 · 原文

GPT-5.6 helped break Chrome’s defenses for a $250,000 Google bounty.

Xbow engineer Brendan Dolan-Gavitt ran OpenAI’s gpt-5.6-sol, against the browser’s source code over six days and $40,000 of compute

The agents searched code, tested hypotheses, and drafted the exploit stages, while Dolan-Gavitt and colleagues picked targets, supplied context, and decided which pieces to join.

Reconstructing the Codex logs, Xbow put the compute bill at roughly $40,000, a fraction of the prize, and well below the months of specialist labor such work once demanded.

The finished chain turned ordinary JavaScript in a Chrome tab into code running outside every sandbox, crossing two protective boundaries through three separate flaws.
Google reproduced the chain, confirmed all three bugs, shipped fixes, and awarded the first $250,000 full-chain Chrome reward under rules it set

来源:Rohan Paul · x.com