TGTGInsighttelegram intelligenceLIVE / telegram public index
Post content
Post content
π Two OpenAI flaws showed how AI systems can expose sensitive data. πΈ One allowed silent leaks via a DNS side channel in ChatGPT πΈ Another enabled GitHub token theft via Codex injection π What these vulnerabilities exposed about AI security β https://thehackernews.com/2026/03/openai-patches-chatgpt-data.html