Hackers chained a heap overflow and SSO flaw to breach OpenAI employee accounts in 72 hours
ccerrato147 · x · 2026-09-18
Security team Hacktron AI disclosed that on July 25 they compromised OpenAI internal systems in under 72 hours via a two-vulnerability chain:
- Exploit chain: HEIF image upload on OpenAI's Discourse forum triggered a libheif heap overflow → RCE, then chained with an OpenAI SSO identity flaw to take over employees' ChatGPT and Codex accounts.
- Proof of impact: They used an employee's Codex to open a harmless PR in OpenAI's internal monorepo, demonstrating potential access to connected GitHub, Slack, and email.
- Remediation: OpenAI fixed the SSO issue roughly 14 hours after the report and paid a $6,500 bounty.
The researchers stress they avoided reading sensitive data, coordinated disclosure with OpenAI and Discourse, and published a full technical write-up. The poster mocks OpenAI's stance of lecturing the world on AI security while its own defenses fell.
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