https://cybersecpro.me/tags/prompt-injection/Recent content in Prompt Injection on Juan Carlos MuneraHugo -- gohugo.ioen© 2026 Juan Carlos MuneraWed, 13 May 2026 00:00:00 +0000https://cybersecpro.me/posts/ai-jailbreak-zero-day-google-gtig/Wed, 13 May 2026 00:00:00 +0000https://cybersecpro.me/posts/ai-jailbreak-zero-day-google-gtig/Google’s threat researchers caught the first zero-day exploit they believe was built with AI assistance. The technique attackers used to get the AI to help is the part worth understanding.https://cybersecpro.me/posts/chatgpt-dns-exfiltration-ai-runtime/Mon, 30 Mar 2026 00:00:00 +0000https://cybersecpro.me/posts/chatgpt-dns-exfiltration-ai-runtime/Check Point Research disclosed a ChatGPT vulnerability that used DNS tunneling to silently exfiltrate conversation data from an isolated runtime. The technique is decades old. The blind spot that enabled it is not.