Last seen September 18, 2026

News report

Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm

Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm finance.biggo.com

Category
News
Lifecycle Status

STABLE

Sources

What Happened

Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm finance.biggo.com

Why This Matters

This is source reporting of a security event, not a confirmed product vulnerability or patchable CVE. Use it as situational awareness if named organizations, cloud tenants, or identity systems overlap with yours.

Recommended Action

Read the source report. Confirm whether any named organizations, identity tenants, or cloud environments you operate are implicated. Do not treat this as a vendor advisory unless a CVE or official bulletin is attached.

Exposure

My Interests Exposure

Exposure unknown

Recommended Response
Last Seen

Sep 18, 2026 22:46

Exposure reason: This incident does not currently match a technology in My Interests.

Exploitation status: UNKNOWN

Primary entities:

AnthropicGitHubGoogleMetaMicrosoftOpenAI

Timeline

  • Incident first seen
    May 28, 2026 12:30

    BugSkan first recorded this incident.

  • TrendAIā„¢ Deploys Claude Opus 4.8 to Advance Vulnerability Detection and Risk Mitigation - TradingView
    May 28, 2026 12:30

    news.google.com Ā· Research

  • Morning Minute: Massive ZCash Exploit Found by Claude, Extent Unknown - Yahoo Finance
    Jun 05, 2026 12:30

    news.google.com Ā· Vulnerability

  • Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm - finance.biggo.com
    Sep 18, 2026 15:35

    news.google.com Ā· News

  • Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company's internal codebase ā€” attackers initiated a 'harmless' pull request as proof of the hack - tomshardware.com
    Sep 18, 2026 19:15

    news.google.com Ā· Malware

  • Researchers used Claude to hack OpenAI employees' ChatGPT accounts
    Sep 18, 2026 22:46

    theregister.com Ā· Vulnerability

  • Latest observed development
    Sep 18, 2026 22:46

    Most recent source or update associated with this incident.

Sources

TrendAIā„¢ Deploys Claude Opus 4.8 to Advance Vulnerability Detection and Risk Mitigation - TradingView

news.google.com Ā· May 28, 2026 12:30

TrendAIā„¢ Deploys Claude Opus 4.8 to Advance Vulnerability Detection and Risk Mitigation TradingView

Open publisher source
Morning Minute: Massive ZCash Exploit Found by Claude, Extent Unknown - Yahoo Finance

news.google.com Ā· Jun 05, 2026 12:30

Morning Minute: Massive ZCash Exploit Found by Claude, Extent Unknown Yahoo Finance

Open publisher source
Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm - finance.biggo.com

news.google.com Ā· Sep 18, 2026 15:35

Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm finance.biggo.com

Open publisher source
Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company's internal codebase ā€” attackers initiated a 'harmless' pull request as proof of the hack - tomshardware.com

news.google.com Ā· Sep 18, 2026 19:15

Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company's internal codebase ā€” attackers initiated a 'harmless' pull request as proof of the hack tomshardware.com

Open publisher source
Researchers used Claude to hack OpenAI employees' ChatGPT accounts

theregister.com Ā· Sep 18, 2026 22:46

Agentic exploits for the win (again)

Open publisher source

Other BugSkan incidents that share identifiers, products, or vendors with this report.

My Interests Match

Want personalized relevance?

Create an account to see which incidents overlap with your interests.

ā† Back to incident intelligence