Rohan Paul (@rohanpaul_ai) · 10/14/2026, 10:58:37
GPT-5.6 Agent Breaks Chrome Sandbox for $250k Google Bounty with $40k Compute Cost
An autonomous agent powered by OpenAI's GPT-5.6 constructed a full-chain exploit bypassing two Chrome sandbox boundaries, earning the first $250,000 Google bounty under new rules. Over six days and ~$40,000 in compute, the agent autonomously searched code, tested hypotheses, and drafted exploit stages, while humans provided strategic context, drastically reducing the labor intensity of traditional security research.
SOURCE COVERAGEFull Original Report
Rohan Paul (@rohanpaul_ai) · 2026-10-14 02
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
