Claude Opus 5 reportedly helped researchers build an exploit path to OpenAI's internal GitHub repository
The New Stack reports that security researchers chained two vulnerabilities, starting with a forum image upload, in under 72 hours.
TLDR
Security researchers used Claude Opus 5 to chain two vulnerabilities into a path from a forum image upload to OpenAI's internal GitHub repository in under 72 hours, The New Stack reports.
Claude Opus 5 reportedly helped researchers build an exploit path to OpenAI's internal GitHub repository
The New Stack reports that security researchers chained two vulnerabilities, starting with a forum image upload, in under 72 hours.
TLDR
Security researchers used Claude Opus 5 to chain two vulnerabilities into a path from a forum image upload to OpenAI's internal GitHub repository in under 72 hours, The New Stack reports.