Description
Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| Microsoft | Visual Studio Code | 1.0.0 – < 1.104.0 | 1.104.0 |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
Third-party code, not reviewed by us. Public PoCs are sometimes fake or contain malware. Read the code first and run it only in an isolated lab, against systems you are authorised to test.
GitHub 1 repository
-
nephila016/CVE-2025-55319-PoC ★ 0 · Jul 11, 2026
PoC for CVE-2025-55319
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Advisories 2
- MSRC-CVE-2025-55319 Agentic AI and Visual Studio Code Remote Code Execution Vulnerability Microsoft Security Response Center · Feb 20, 2026
- WID-SEC-2025-2044 Microsoft Visual Studio Code: Schwachstelle ermöglicht Codeausführung BSI CERT-Bund (WID) · Sep 14, 2025
References
- Agentic AI and Visual Studio Code Remote Code Execution Vulnerability vendor-advisory patch