CVSS 3.1
6.5 mediumCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:NCVE-2026-2256
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.
Severity
- EPSS
- 1.7% chance of exploitation in the next 30 days; higher than 77% of CVEs (scores of 2026-10-31)
- CWE
- CWE-77
- Published
- Modified
- Record from
- the NVD, synced
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-4gc2-344q-r2rw | PyPI | ms-agent | <=1.6.0rc1 | no fix published |
| PYSEC-2026-2668 | PyPI | ms-agent | <=1.6.0rc1 | no fix published |
References
- https://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC
- https://github.com/modelscope/ms-agent
- https://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326
- https://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
- https://www.kb.cert.org/vuls/id/431821