HeraldLoop
← Back to feed
4 sourcesTracking since 18 Sept, 10:30

Researchers used Anthropic’s Claude to access OpenAI accounts and code repository

In brief

Three researchers at Hacktron used Anthropic’s Claude Opus 5 to chain vulnerabilities and gain access to several OpenAI employees’ ChatGPT and Codex accounts. One compromised account provided access to an internal OpenAI code repository. The effort took less than 72 hours, and OpenAI paid the researchers a $6,500 bounty.

Summary written by HeraldLoop from 4 sources · updated 23h ago

What changed

  1. 18 Sept, 10:30White Hats Used Anthropic’s Claude to Break Into OpenAI in 72 Hours · Bitcoin.com News
  2. 18 Sept, 16:29Researchers Earned $6,500 Breaching OpenAI With Anthropic's Claude · BeInCrypto
  3. 19 Sept, 00:40Anthropic’s Claude helped 3 researchers breach OpenAI in under 72 hours · CryptoSlate
  4. 19 Sept, 18:36Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws · The Hacker News
ShareXWhatsAppFacebookLinkedIn

How outlets framed it

Anthropic3 sources
33% favorable (1)67% neutral (2)0% critical (0)

favorable: BeInCrypto.

Show how each outlet framed it
OpenAI3 sources
0% favorable (0)100% neutral (3)0% critical (0)

All 3 sources reported it neutrally.

Show how each outlet framed it

One source, one vote (its latest article in the story). Only labels with confidence ≥ 0.6 are shown; the quote is the evidence.

Chronological coverage

  1. 19 September
  2. Latest19 Sept, 18:36

    Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws

    Three researchers at the security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help forum and moved through a weakness in OpenAI's own login system. This was security research,

    The Hacker NewsThe Hacker News•info@thehackernews.com (The Hacker News)
  3. Follow-up19 Sept, 00:40

    Anthropic’s Claude helped 3 researchers breach OpenAI in under 72 hours

    Anthropic’s Claude helped three security researchers breach OpenAI accounts and reach an internal code repository within 72 hours. Researchers at cybersecurity startup Hacktron chained an image-processing vulnerability with a flaw in OpenAI’s identity infrastructure in July to gain access to multiple employees’ ChatGPT and Codex accounts. One compromised Codex account was connected to OpenAI’s GitHub […]

    CryptoSlateCryptoSlate•Oluwapelumi Adejumo
  4. 18 September
  5. Follow-up18 Sept, 16:29

    Researchers Earned $6,500 Breaching OpenAI With Anthropic's Claude

    A rival’s own AI model ended up doing the heavy lifting in a breach against OpenAI. Researchers at Hacktron AI used Anthropic’s Claude to write working exploit code. The entire intrusion took under 72 hours. OpenAI ultimately paid a $6,500 bounty once the team proved they had reached its private source code. How an Image

    favorable toward Anthropic
    BeInCryptoBeInCrypto•Luis Blanco
  6. First seen18 Sept, 10:30

    White Hats Used Anthropic’s Claude to Break Into OpenAI in 72 Hours

    A small team of researchers chained three bugs with Anthropic’s Claude Opus 5 and ended up inside OpenAI’s private code repository. The whole job took under 72 hours, and OpenAI paid $6,500 for it. The Chain, Link by Link A vulnerable ‘libheif’ library inside Discourse, the forum software, allowed remote code execution (RCE) on the […]

    Bitcoin.com NewsBitcoin.com News•Shiraz Jagati