Skip to content
Threat Feed

CPE

Cpe:2.3:a:microsoft:semantic_kernel:*:*:*:*:*:python:*:*

1 brief RSS
critical advisory

AI Agent Frameworks Vulnerable to RCE via Prompt Injection

AI agents using frameworks like Microsoft's Semantic Kernel are vulnerable to remote code execution (RCE) via prompt injection by manipulating plugin parameters due to unsafe data handling.

Semantic Kernel ai prompt-injection rce semantic-kernel
2r 1t 2c