CVE-2026-2256 PUBLISHED

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input.

• https://github.com/modelscope/ms-agent
• https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
• https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326
• https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC

• CWE-94 Improper Control of Generation of Code ('Code Injection')