Cyber Posture

CVE-2026-7211

High

Published: 28 April 2026

Published
28 April 2026
Modified
29 April 2026
KEV Added
Patch
CVSS Score 7.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
EPSS Score 0.0218 84.5th percentile
Risk Priority 16 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2026-7211 is a high-severity Injection (CWE-74) vulnerability. Its CVSS base score is 7.3 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked in the top 15.5% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.

The strongest mitigations our analysis identified are NIST 800-53 SI-10 (Information Input Validation) and SI-2 (Flaw Remediation).

Threat & Defense at a Glance

What attackers do: exploitation maps to Exploit Public-Facing Application (T1190) and 1 other technique. What defenders deploy: see the NIST 800-53 controls recommended below.
Threat & Defense Details

Mitigating Controls (NIST 800-53 r5)AI

prevent

SI-10 mandates information input validation at entry points like the GitSearchRequest function, directly preventing command injection via manipulated repo_url/pattern arguments.

prevent

SI-2 requires identification, reporting, and correction of flaws in system components, directly addressing remediation of this known command injection vulnerability.

prevent

AC-6 enforces least privilege for processes handling the Git Search API, limiting the scope and impact of arbitrary commands injected through repo_url/pattern.

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
Why these techniques?

Command injection in public-facing Git Search API enables T1190 (Exploit Public-Facing Application) for remote unauthenticated RCE; directly facilitates T1059 (Command and Scripting Interpreter) for arbitrary command execution on the server.

Confidence: HIGH · MITRE ATT&CK Enterprise v18.1

NVD Description

A weakness has been identified in dvladimirov MCP up to 0.1.0. The impacted element is the function GitSearchRequest of the file mcp_server.py of the component Git Search API. Executing a manipulation of the argument repo_url/pattern can lead to command injection.…

more

The attack can be executed remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

Deeper analysisAI

CVE-2026-7211 is a command injection vulnerability affecting dvladimirov MCP versions up to 0.1.0. The issue resides in the GitSearchRequest function within the mcp_server.py file of the Git Search API component. By manipulating the repo_url/pattern argument, an attacker can inject malicious commands, as identified under CWEs-74 and CWE-77. The vulnerability carries a CVSS v3.1 base score of 7.3 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L), indicating high severity due to its network accessibility and lack of prerequisites.

Remote attackers require no privileges or user interaction to exploit this vulnerability over the network with low complexity. Successful exploitation allows limited impacts on confidentiality, integrity, and availability, potentially enabling arbitrary command execution on the server hosting the MCP Git Search API.

Advisories from VulDB (vuldb.com/vuln/359807) note that the project was informed early via GitHub issue #2 (github.com/dvladimirov/MCP/issues/2), but has not yet responded or released patches. No mitigations or fixes are currently available.

A public exploit is available, increasing the risk of real-world attacks against unpatched instances of this software.

Details

CWE(s)

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: mcp

CVEs Like This One

CVE-2026-2178Shared CWE-74, CWE-77
CVE-2026-7812Shared CWE-74, CWE-77
CVE-2026-7215Shared CWE-74, CWE-77
CVE-2026-7316Shared CWE-74, CWE-77
CVE-2026-6980Shared CWE-74, CWE-77
CVE-2026-7157Shared CWE-74, CWE-77
CVE-2026-1066Shared CWE-74, CWE-77
CVE-2025-15133Shared CWE-74, CWE-77
CVE-2025-8752Shared CWE-74, CWE-77
CVE-2025-0328Shared CWE-74, CWE-77

References