Get the app
Cybersecurity5 min reading time

Researchers used Anthropic’s Claude to hack into OpenAI

Covered by 3 sources
Read full post
Security researchers from Hacktron AI used Anthropic's Claude model to exploit vulnerabilities in OpenAI's systems, gaining access to employee ChatGPT accounts and software. OpenAI patched the issues and rewarded the team $6,500 through its bug bounty program. This incident underscores growing AI security challenges as off-the-shelf AI tools become capable of sophisticated cyberattacks.

Covered by 3 sources

#anthropic#bug-bounty#chatgpt#claude#hacktron-ai#openai#security-research

More in Cybersecurity

Cybersecurity3 min read

This tiny cybersecurity startup managed to hack OpenAI using Claude, and won a $6,500 bounty

Covered by 3 sources
Cybersecurity

Hackers Used Anthropic’s Claude to Break Into OpenAI

Covered by 3 sources
Cybersecurity4 min read

WSO2 Releases Agent Manager as Enterprises Look to Control Growing AI Agent Sprawl

InfoQ (AI, ML & Data)