CVE-2026-7316
Published: 28 April 2026
Summary
CVE-2026-7316 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 command injection vulnerability tracked as CVE-2026-7316 affects the eiliyaabedini aider-mcp project up to commit 667b914301aada695aab0e46d1fb3a7d5e32c8af. The issue resides in an unknown function within the aider_mcp.py file of the code_with_ai component, where manipulation of the working_dir and editable_files arguments permits injection of operating system commands. The project follows a rolling release model, so no discrete version numbers are provided for affected or fixed releases. The flaw is classified under CWE-74 and CWE-77 and carries a CVSS 4.0 score of 5.5 with network attack vector and no required privileges or user interaction.
Remote attackers can exploit the weakness without authentication to execute arbitrary commands on the host running the affected component. Publicly disclosed proof-of-concept material indicates that successful exploitation can alter or access files and processes within the scope of the running application, though the CVSS metrics reflect only limited impacts to confidentiality, integrity, and availability.
The GitHub repository and associated issue tracker contain the disclosure report, yet the maintainer has not responded to the early notification. No official patches, workarounds, or mitigation guidance have been published.
The EPSS score has remained low, moving only from a peak of 0.0218 to a current value of 0.0212.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-26153
Vulnerability details
A vulnerability has been found in eiliyaabedini aider-mcp up to 667b914301aada695aab0e46d1fb3a7d5e32c8af. Affected is an unknown function of the file aider_mcp.py of the component code_with_ai. The manipulation of the argument working_dir/editable_files leads to command injection. The attack may be initiated remotely.…
more
The exploit has been disclosed to the public and may be used. This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available. 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?
Command injection in remotely accessible application (AV:N, unauth) directly enables T1190 for initial access via public-facing app exploitation and T1059 for arbitrary command execution on the host.
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Directly prevents command injection by requiring validation of manipulated arguments like working_dir/editable_files before processing in aider_mcp.py.
Enforces restrictions on types and sources of inputs to block command injection attacks exploiting the code_with_ai component.
Requires timely identification and remediation of the specific command injection flaw up to commit 667b914301aada695aab0e46d1fb3a7d5e32c8af.