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.
CVE-2026-2256
Score 6.5 from GitHub Security Advisory published 2026-03-02. CISA-ADP (Vulnrichment) CVSS v3.1 baseline 6.5; sources differ by 0.0.
- Lower severity and no public exploit yet
No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.
- CVSS v3
- 6.5
- EG Score
- 6.5(medium)
- EG Risk
- 34(Track)EG Risk 34/100SSVC: Track
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity65% × 45%Exploitation0% × 40%Automatability30% × 15%Action: Routine — remediate on your standard cadence. - EPSS PROB
- 2%
- EPSS %ILE
- 73%
- KEV
- Not listed
Published
March 2, 2026
Last Modified
June 17, 2026
References (5)
- cret@certhttps://github.com/Itamar-Yochpaz/CVE-2026-2256-PoC
- cret@certhttps://github.com/modelscope/ms-agent
- cret@certhttps://medium.com/@itamar.yochpaz/cve-2026-2256-from-ai-prompt-to-full-system-compromise-a4114c718326
- cret@certhttps://www.hiddenlayer.com/research/indirect-prompt-injection-of-claude-computer-use
- af854a3a-2127-422b-91ae-364da2661108https://www.kb.cert.org/vuls/id/431821
Patch Availability(1)
| Vendor / Ecosystem | Fixed in / Patch | Released | Source |
|---|---|---|---|
| pip | ms-agent | — | ghsa |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 3× in last 7d / 3× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.
- 2026-07-28 15:36 UTCEPSS rescore
- 2026-07-27 13:56 UTCEG score recompute
- 2026-07-27 13:56 UTCGHSA enrichment
Related CVEs(same CWE)
Same CWE
10 shownCWE-77
- CVE-2015-7541EG 10.0CRITICAL
- CVE-2015-1815EG 10.0EPSS p97HIGH
- CVE-2014-1905EG 10.0EPSS p95HIGH
- CVE-2013-2810EG 10.0EPSS p93HIGH
- CVE-2014-5470EG 9.8EPSS p95CRITICAL
- CVE-2013-2513EG 9.8CRITICAL
- CVE-2015-20108EG 9.8CRITICAL
- CVE-2015-10096NVD 5.0EG 9.8CRITICAL
- CVE-2015-20107NVD 7.6EG 9.8EPSS p94CRITICAL
- CVE-2014-4982EG 9.8EPSS p91CRITICAL
Frequently asked(5)
What is CVE-2026-2256?
When was CVE-2026-2256 disclosed?
Is CVE-2026-2256 actively exploited?
What is the CVSS score of CVE-2026-2256?
How do I remediate CVE-2026-2256?
Dependency Blast Radius
Explore the affected products and dependency analysis for CVE-2026-2256
Is Your Infrastructure Affected by CVE-2026-2256?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.