Hacktron AI team breached OpenAI in 72 hours via two flaws, hijacked ChatGPT accounts
FinanceYF5 · x · 2026-09-20
According to this thread, on July 25, 2026, the Hacktron AI team breached OpenAI in under 72 hours using two vulnerabilities:
- Took over ChatGPT and Codex accounts of some OpenAI employees and external users
- Gained access to linked Outlook, Slack, and GitHub services
- Submitted a PR to OpenAI's internal codebase as proof of the breach
A link to the full write-up is included. Note this is a third-party retelling; details should be verified against the original report.
More from Safety
- Hundreds of offensive ARTEX AI agents deployed across VPS providers, hitting Korean banks — IgorCarron · 2026-11-04
- UK NCSC: AI will speed up and scale existing cyber attacks, not create new ones — koltregaskes · 2026-11-04
- Anthropic says it may imminently hit RSP threshold for AI-accelerated R&D, releases provable inference work — tobyordoxford · 2026-11-04
- Hackers reset French blood service freezers from -30°C to 110°C in supply-chain cyberattack — LuizaJarovsky · 2026-11-04
- Google says it removed post-employment non-disparagement clauses from new-hire terms — HaydnBelfield · 2026-11-04
- Claude doesn't really forget: Anthropic's privacy policy allows records retention up to 7 years — nikola_mr64990 · 2026-11-04