TechResearchers use Anthropic's Claude to breach OpenAI systems in bug-bounty demonstration
Hacktron AI researchers used Claude to chain vulnerabilities in Discourse hosting OpenAI's forum, including HEIF/HEIC image processing flaw, accessing employee accounts and internal GitHub repos. Attack completed in under 72 hours and $3,000 in tokens; researchers received $6,500 bounty.
TLDR
Illustrates AI's dual-use potential for offensive security and competitive dynamics between labs. Shows how quickly AI models can accelerate vulnerability exploits and chain attacks. Part of broader narrative on AI agents in the wild and real-world impact of model capabilities.
Researchers use Anthropic's Claude to breach OpenAI systems in bug-bounty demonstration
Hacktron AI researchers used Claude to chain vulnerabilities in Discourse hosting OpenAI's forum, including HEIF/HEIC image processing flaw, accessing employee accounts and internal GitHub repos. Attack completed in under 72 hours and $3,000 in tokens; researchers received $6,500 bounty.
