Improper control of generation of code ('code injection') in Visual Studio Tools for Applications and SQL Server Management Studio allows an unauthorized attacker to execute code over a network.
How could an attacker exploit this vulnerability? The AV:N rating indicates the vulnerability is exploitable over the network, meaning an attacker can deliver a malicious prompt remotely without prior access, while UI:R means a user must interact with Copilot for exploitation to occur. Due to prompt injection, the system is coerced into executing attacker-controlled instructions, which can escalate into remote code execution (RCE) when the compromised prompt causes backend components or integrated tools to run unintended commands.
<a href="https://twitter.com/wunderwuzzi23">Johann Rehberger</a> with https://embracethered.com/