Lucene search
K

When prompts become shells: RCE vulnerabilities in AI agent frameworks

🗓️ 07 May 2026 20:22:39Reported by Microsoft Defender Security Research Team, Uri Oren, Amit Eliahu and Dor EdryType 
mssecure
 mssecure
🔗 www.microsoft.com👁 146 Views

This article highlights prompt injection risks and remote code execution in AI agent frameworks.

Related
ReporterTitlePublishedViews
Family
GithubExploit
Exploit for Code Injection in Microsoft
22 Jun 202611:28
githubexploit
GithubExploit
Exploit for CVE-2026-26030
24 Feb 202616:50
githubexploit
ATTACKERKB
CVE-2026-25592
6 Feb 202620:38
attackerkb
Circl
CVE-2026-25592
6 Feb 202621:21
circl
Circl
CVE-2026-26030
19 Feb 202618:01
circl
CNNVD
Microsoft Semantic Kernel 代码注入漏洞
19 Feb 202600:00
cnnvd
CNNVD
Microsoft Semantic Kernel 路径遍历漏洞
6 Feb 202600:00
cnnvd
CNVD
Microsoft Semantic Kernel Code Injection Vulnerability
6 Mar 202600:00
cnvd
CVE
CVE-2026-25592
6 Feb 202620:38
cve
CVE
CVE-2026-26030
19 Feb 202616:00
cve
Rows per page

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation