White-hat researchers used anthropic's claude to get into an openai employee's chatgpt account and…
white-hat researchers used anthropic's claude to get into an openai employee's chatgpt account and read openai's private code caches — openai paid them $6,500. the tools you ship can be used against you by the same agent vendors' models.
security teams are now on both sides of the same agent.
Context
Secondary coverage dated 18 and 22 September 2026 says a small team, Hacktron AI, chained two vulnerabilities, an RCE through image processing on OpenAI's Discourse forum and an SSO weakness, with help from Claude Opus 5, and reported it through Bugcrowd on 25 July 2026. Hacktron's timeline says the chain reached multiple employee ChatGPT accounts and internal repositories in under 72 hours. The coverage says OpenAI fixed its side about 14 hours after the report and paid 6,500 dollars, and that the award covered its identity flaw, not testing of the out-of-scope Discourse forum.
All of this rests on secondary coverage; Hacktron's own writeup and OpenAI's statement were not inspected. The coverage says the episode did not establish that Claude autonomously breached OpenAI or that the researchers copied private source code, so read private code caches and Claude got into the account are broader than the sources. The writeup's claim is that access was proven through a connected Codex account. The 6,500 dollar figure is secondary.
Related work
- OpenAI hacked by white-hat researchers (Bitcoin.com News, 18 Sep 2026) ↗Secondary; text read.
Watch next
- Hacktron's own report and OpenAI's bounty statement.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 07:21 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →