HighVulnerabilityLLM-specific

CVE-2026-2256: ModelScope ms-agent command injection through prompt-derived input

Source: NVD(opens in a new tab)
Identifier: CVE-2026-2256
Published: March 2, 2026
Record updated: October 9, 2026

Affected: ms-agent <= 1.6.0rc1
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.7%

Summary

CVE-2026-2256 is a command injection vulnerability in ModelScope's ms-agent, versions v1.6.0rc1 and earlier. It allows an attacker to execute arbitrary operating system commands through crafted prompt-derived input. NVD has not yet provided an assessment, and the record was published 03/02/2026.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

EPSS: 1.7%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051

Affected

Packages: ms-agent@<= 1.6.0rc1
Vendors: Anthropic

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-2256

First tracked: March 2, 2026 at 07:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 85% (self-assessed)

Summary

Mitigation

Related items