CVE-2026-7206
Published: 28 April 2026
Summary
CVE-2026-7206 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 at the 15.2th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Data-Related Vulnerabilities risk domain.
The strongest mitigations our analysis identified are NIST 800-53 RA-5 (Vulnerability Monitoring and Scanning) and SI-10 (Information Input Validation).
Deeper analysis
CVE-2026-7206 is a SQL injection vulnerability (CWE-74, CWE-89) affecting dubydu sqlite-mcp versions up to 0.1.0. The issue lies in the extract_to_json function within the src/entry.py file, where manipulation of the output_filename argument enables injection of malicious SQL code. Published on 2026-04-28, it 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 flaw over the network with low attack complexity. Exploitation allows limited impacts on confidentiality, integrity, and availability, potentially enabling unauthorized data access, modification, or disruption via injected SQL commands. A public exploit has been released, increasing the risk of active attacks.
Mitigation involves applying the patch commit a5580cb992f4f6c308c9ffe6442b2e76709db548 from the project's GitHub repository, as recommended in the advisory. Additional details are available in the related GitHub issue, pull request, and VulDB submission.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-25963
Vulnerability details
A security flaw has been discovered in dubydu sqlite-mcp up to 0.1.0. The affected element is the function extract_to_json of the file src/entry.py. Performing a manipulation of the argument output_filename results in sql injection. Remote exploitation of the attack is…
more
possible. The exploit has been released to the public and may be used for attacks. The patch is named a5580cb992f4f6c308c9ffe6442b2e76709db548. Applying a patch is the recommended action to fix this issue.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Data-Related Vulnerabilities
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The remote SQL injection vulnerability in a network-accessible component with no authentication required directly enables exploitation of public-facing applications for initial access and limited data manipulation.
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Directly mitigates the CVE by requiring timely patching of the SQL injection flaw in extract_to_json as recommended in the advisory.
Prevents SQL injection exploitation by validating the manipulated output_filename argument before processing.
Identifies the SQL injection vulnerability in sqlite-mcp through regular scanning for known CVEs like CVE-2026-7206.