CVE-2026-7215
Published: 28 April 2026
Summary
CVE-2026-7215 is a medium-severity Injection (CWE-74) vulnerability. Its CVSS base score is 5.5 (Medium).
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).
Deeper analysis
A security flaw has been discovered in egtai gmx-vmd-mcp up to version 0.1.0. The issue resides in the launch_vmd_gui_tool function within mcp_server.py of the VMD Launch Handler component, where manipulation of the structure_file or trajectory_file arguments enables command injection. The vulnerability is tracked under CWE-74 and CWE-77, carries a CVSS 4.0 score of 5.5, and permits remote attacks without requiring authentication or user interaction.
Remote attackers can supply crafted arguments to execute arbitrary commands on the affected system, resulting in limited impacts to confidentiality, integrity, and availability. A public exploit has already been released, increasing the likelihood of active abuse against unpatched instances.
The referenced GitHub repository and associated issue report indicate that maintainers were notified via an issue submission but have not issued a response or patch. No mitigation guidance or updated releases are documented in the available references.
The EPSS score remains low with negligible movement between its current value of 0.0212 and recorded peak of 0.0218, and no confirmed real-world exploitation campaigns have been reported.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-25971
Vulnerability details
A security flaw has been discovered in egtai gmx-vmd-mcp up to 0.1.0. This issue affects the function launch_vmd_gui_tool of the file mcp_server.py of the component VMD Launch Handler. The manipulation of the argument structure_file/trajectory_file results in command injection. The attack…
more
may be launched remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
- 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
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Remote command injection in public-facing server component (mcp_server.py) directly enables exploitation of public-facing applications (T1190) and arbitrary command execution via scripting interpreter (T1059).
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Directly mitigates command injection by validating and sanitizing the structure_file and trajectory_file arguments in launch_vmd_gui_tool to prevent malicious command execution.
Requires timely identification, reporting, and remediation of the known command injection flaw in egtai gmx-vmd-mcp up to version 0.1.0 once patches become available.
Enforces least privilege on the mcp_server.py process to limit the scope and impact of any successfully injected commands.