))
Prompt Injection to RCE: When AI Gets Compromised | The AppSec Insiders Ep.16
Manage episode 496485038 series 3482903
Kandungan disediakan oleh Farshad Abasi. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh Farshad Abasi atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.
In this episode, we unpack CVE-2025-49596, where prompt injection, CSRF, and localhost access were chained to achieve RCE in the MCP Inspector AI tool. Learn how the exploit worked, what it reveals about LLM security risks, and how to defend against similar threats with sandboxing, access controls, and DevSecOps monitoring.
18 episod
Kongsi
