NEWS
Parameter Labs Discovers Account Takeover Vulnerability in ChatGPTThe research team discovered a complex exploit chain that leaked from HTML previews in the sandbox to the homepage to steal user data. OpenAI patched the vulnerability and paid a $5,000 bug bounty. This is a news summary compiled for the AiPulse newsletter — not the original article. The original article is at simonwillison.net. Read the original article AI Critique → English (automatic translation) |