Researchers used Claude Opus 5 to chain a Discourse flaw into OpenAI's private code
rohanpaul_ai · x · 2026-09-18
Per WSJ, three researchers used Claude Opus 5 to automate a vulnerability chain that turned a Discourse flaw into access to OpenAI's private code. Tokens harvested from the forum included OpenAI employees', and some worked on ChatGPT and reached OpenAI's GitHub — bridging one identity boundary into another. OpenAI's review found only "limited reads" of private-repo metadata and code changes; no model weights believed exposed.
More from Safety
- 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
- Polymarket opens a market on Anthropic's next AI sandbox escape — Polymarket · 2026-11-04
- Rival company blames 'AI gone off the rails' after founder catches it hacking his network — AccBalanced · 2026-11-04