---
type: "post"
id: "xbow-built-a-chrome-full-chain-exploit-affecting-097c4b"
slug: "xbow-built-a-chrome-full-chain-exploit-affecting-097c4b"
title: "XBOW Built a Chrome Full-Chain Exploit Affecting a Billion Users in Six Days"
description: "XBOW’s account reports that four researchers and GPT-5.6 Sol built a Chrome full-chain exploit in six days, after Google said one bug in their first chain was already known."
retrieval_nugget: "XBOW’s account reports that four researchers and GPT-5.6 Sol built a Chrome full-chain exploit in six days, after Google said one bug in their first chain was already known."
published_at: "2026-10-14"
updated_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "published_at"
topics: ["google"]
source_urls: ["https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:xbow-built-a-chrome-full-chain-exploit-affecting-097c4b"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:f05aeb6e9334998dca5e34a969c826b0ddc8961117ec0d16c84e64522fde7d6e","reviewed_at":"2026-10-14T16:11:11.618Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"AI-assisted vulnerability research is becoming a faster human-led search loop, not yet demonstrated autonomous discovery.","observed_facts":[{"text":"XBOW says four researchers used GPT-5.6 Sol to build a Chrome full-chain exploit in six days.","source_urls":["https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit"]},{"text":"XBOW says Google awarded a $250,000 bounty and compute for the awarded chain cost $40,000.","source_urls":["https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit"]},{"text":"XBOW says Google had identified one bug in the initial chain; the researchers used prepared alternatives to build a replacement chain.","source_urls":["https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit"]},{"text":"XBOW says the three bugs in the chain have been fixed.","source_urls":["https://xbow.com/blog/xbow-built-a-chrome-full-chain-exploit"]}],"mechanism":"The model searched Chrome source code, tested ideas, built proofs of concept and drafted early exploit versions; researchers chose strategy, checked work and redirected the agents. Preparing alternative chain components let the team replace a bug Google already knew about.","why_now":"XBOW has published its account of a high-impact chain and says the bugs are fixed, making the reported workflow and its limits relevant to defenders evaluating AI-assisted vulnerability research.","implications":["AI assistance can compress parts of vulnerability research, but the reported result depended on researcher direction, validation and prior work.","Defenders can apply similar search and testing to their own software, but must verify outputs and measure whether the loop yields fixes."],"evidence_boundary":"The timeline, model role, costs and bounty come from XBOW; the post does not independently establish reproducibility, comparative performance, or how often the method succeeds.","watch_conditions":["Whether other teams reproduce this speedup on independently assessed targets, and whether defenders can turn it into a measurable increase in verified fixes."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied; this is a distinct source-grounded case of human-directed AI security research."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/xbow-built-a-chrome-full-chain-exploit-affecting-097c4b/","markdown":"https://newruntime.com/posts/xbow-built-a-chrome-full-chain-exploit-affecting-097c4b.md","json":"https://newruntime.com/posts/xbow-built-a-chrome-full-chain-exploit-affecting-097c4b.json"}
---

# XBOW Built a Chrome Full-Chain Exploit Affecting a Billion Users in Six Days

## Retrieval answer

XBOW’s account reports that four researchers and GPT-5.6 Sol built a Chrome full-chain exploit in six days, after Google said one bug in their first chain was already known.

XBOW’s account reports that four researchers and GPT-5.6 Sol built a Chrome full-chain exploit in six days, after Google said one bug in their first chain was already known. The awarded chain cost $40,000 in compute, and Google paid a $250,000 bounty. Those are the reported facts; the source is XBOW’s own account, not an independent audit.

Thesis: AI-assisted vulnerability research is becoming a faster human-led search loop, not yet demonstrated autonomous discovery. Mechanism: The model searched Chrome source code, tested ideas, built proofs of concept and drafted early exploit versions; researchers chose strategy, checked work and redirected the agents. Preparing alternative chain components let the team replace a bug Google already knew about. The reported six-day result followed earlier work and prior experience, so it should not be read as six days from a blank slate.

Why now: XBOW has published its account of a high-impact chain and says the bugs are fixed, making the reported workflow and its limits relevant to defenders evaluating AI-assisted vulnerability research. Implication: AI assistance can compress parts of vulnerability research, but the reported result depended on researcher direction, validation and prior work. Evidence boundary: The timeline, model role, costs and bounty come from XBOW; the post does not independently establish reproducibility, comparative performance, or how often the method succeeds. Watch condition: Whether other teams reproduce this speedup on independently assessed targets, and whether defenders can turn it into a measurable increase in verified fixes.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)