CVE-2026-2256
6.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| ModelScope | ms-agent | 0 <= v1.6.0rc1 | affected |
Weaknesses
- CWE-94 Improper Control of Generation of Code ('Code Injection')
ADP Enrichment
CVE Program Container
Additional References
CISA ADP Vulnrichment
- SSVC:
- Exploitation: poc
- Automatable: yes
- Technical Impact: partial
References
- 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
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.