---
type: "post"
id: "an-off-the-shelf-openai-model-helped-hack-fa471e"
slug: "an-off-the-shelf-openai-model-helped-hack-fa471e"
title: "An off-the-shelf OpenAI model helped hack Google Chrome : an engineer at security startup Xbow spent $40,000 on GPT-5.6 to chain three unpatched Chrome bugs and won Google's top $250,000 bounty."
description: "## The model is an instrument in a human-led exploit chain"
retrieval_nugget: "## The model is an instrument in a human-led exploit chain"
published_at: "2026-10-14"
updated_at: "2026-10-14"
record_date: "2026-10-14"
date_kind: "published_at"
topics: ["google"]
source_urls: ["https://www.forbes.com/sites/the-wiretap/2026/10/13/how-an-off-the-shelf-openai-model-found-three-google-chrome-zero-days"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:an-off-the-shelf-openai-model-helped-hack-fa471e"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:07fc96b6eec84c7e005aa8bf0a40a2efdd775d9eb98a7856d07b36f912f23fe3","reviewed_at":"2026-10-14T11:02:50.813Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"This case shows a commercially available model participating in high-end vulnerability research, while leaving the human researcher responsible for directing and validating the work.","observed_facts":[{"text":"Forbes reports Xbow engineer Brendan Dolan-Gavitt used GPT-5.6 to chain three previously unpatched Chrome vulnerabilities.","source_urls":["https://www.forbes.com/sites/the-wiretap/2026/10/13/how-an-off-the-shelf-openai-model-found-three-google-chrome-zero-days"]},{"text":"The report says Google confirmed the findings and awarded the maximum $250,000 bounty.","source_urls":["https://www.forbes.com/sites/the-wiretap/2026/10/13/how-an-off-the-shelf-openai-model-found-three-google-chrome-zero-days"]},{"text":"Forbes reports about $40,000 in token spending and says two additional Xbow exploits await Google review.","source_urls":["https://www.forbes.com/sites/the-wiretap/2026/10/13/how-an-off-the-shelf-openai-model-found-three-google-chrome-zero-days"]}],"mechanism":"The engineer prompted the model for ways to crack Chrome’s security and worked with it to generate the chain; the reported $40,000 in token spend is a cost of that collaboration, not a measured cost per validated vulnerability.","why_now":"Commercially accessible models can now contribute to research on widely deployed software, making the boundary between defensive research and attacker capability increasingly consequential.","implications":["Security teams should treat model-assisted vulnerability discovery as a capability available to legitimate researchers and potential attackers, while keeping human review and responsible disclosure central.","The reported spend is not a general benchmark for automated vulnerability discovery economics."],"evidence_boundary":"The account is Forbes’ report, including statements attributed to Xbow and Google; it does not provide an independently reproducible evaluation of how much of the discovery or exploit chain came from the model. It also says two other Xbow exploits await Google review, so those claims should not be treated as confirmed findings.","watch_conditions":["Watch for Google’s disposition of the two additional reported exploits and for technical disclosure that clarifies the model’s actual contribution."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied; this is a distinct, quantified report of GPT-5.6-assisted vulnerability research against Chrome."}
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/an-off-the-shelf-openai-model-helped-hack-fa471e/","markdown":"https://newruntime.com/posts/an-off-the-shelf-openai-model-helped-hack-fa471e.md","json":"https://newruntime.com/posts/an-off-the-shelf-openai-model-helped-hack-fa471e.json"}
---

# An off-the-shelf OpenAI model helped hack Google Chrome : an engineer at security startup Xbow spent $40,000 on GPT-5.6 to chain three unpatched Chrome bugs and won Google's top $250,000 bounty.

## Retrieval answer

## The model is an instrument in a human-led exploit chain

## The model is an instrument in a human-led exploit chain

**Thesis:** This case shows a commercially available model participating in high-end vulnerability research, while leaving the human researcher responsible for directing and validating the work. Forbes reports that Xbow engineer Brendan Dolan-Gavitt used GPT-5.6 to chain three previously unpatched Chrome vulnerabilities. The report says Google confirmed the findings and awarded its maximum $250,000 bounty. **Mechanism:** The engineer prompted the model for ways to crack Chrome’s security and worked with it to generate the chain; the reported $40,000 in token spend is a cost of that collaboration, not a measured cost per validated vulnerability.

**Why now:** Commercially accessible models can now contribute to research on widely deployed software, making the boundary between defensive research and attacker capability increasingly consequential. This is a concrete example in a browser with multiple security layers, including sandboxes, rather than proof that models routinely bypass them. **First implication:** Security teams should treat model-assisted vulnerability discovery as a capability available to legitimate researchers and potential attackers, while keeping human review and responsible disclosure central.

**Evidence boundary:** The account is Forbes’ report, including statements attributed to Xbow and Google; it does not provide an independently reproducible evaluation of how much of the discovery or exploit chain came from the model. It also says two other Xbow exploits await Google review, so those claims should not be treated as confirmed findings. **First watch condition:** Watch for Google’s disposition of the two additional reported exploits and for technical disclosure that clarifies the model’s actual contribution.

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)