Raw vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-7384 is a medium-severity Path Traversal (CWE-22) 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 35th 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 Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-7384 is a path traversal vulnerability (CWE-22) in the ezequiroga mcp-bases project, specifically affecting the search_papers function within the research_server.py file at commits 357ca19c7a49a9b9cb2ef639b366f03aba8bea39 and c630b8ab0f970614d42da8e566e9c0d15a16414c. This flaw allows attackers to manipulate the 'topic' argument to traverse directories and access unintended files. 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) and was published on 2026-04-29.
The vulnerability enables remote exploitation without requiring authentication or user interaction. Attackers can send crafted requests to the affected search_papers endpoint, exploiting the path traversal to read sensitive files, modify data, or disrupt service availability, albeit with low impact levels across confidentiality, integrity, and availability as per the CVSS metrics.
Advisories from VulDB and the project's GitHub repository (ezequiroga/mcp-bases/issues/2) indicate that the issue was reported early, but the maintainers have not yet responded or issued patches. The project uses a rolling release model, providing no specific version details for affected or remediated releases; practitioners should monitor the repository for updates.
The exploit is publicly available, increasing the risk of immediate abuse, though no confirmed real-world exploitation has been reported in the provided details.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-26238
Vulnerability Data
A vulnerability was detected in ezequiroga mcp-bases 357ca19c7a49a9b9cb2ef639b366f03aba8bea39/c630b8ab0f970614d42da8e566e9c0d15a16414c. This impacts the function search_papers of the file research_server.py. Performing a manipulation of the argument topic results in path traversal. Remote exploitation of the attack is possible. The exploit is now public…
more
and may be used. This product follows a rolling release approach for continuous delivery, so version details for affected or updated releases are not provided. 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
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V5.3.2
Mitigating Controls (NIST 800-53 r5) AI
Enforces the intended directory access authorizations that path traversal would otherwise bypass.
Input validation directly neutralizes special path elements before pathname construction occurs.
Least privilege reduces the impact of any unauthorized file access obtained via traversal.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Patching/maintenance can remediate known path-traversal flaws in deployed software (partial prevention of exploitability) but does nothing to stop the coding defect from being introduced in the first place.
PR.AA-05 defines and reviews access policies but does not address code-level pathname neutralization, so neither direction prevents CWE-22.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Security testing in development catches path traversal via static/dynamic analysis.
Secure SDLC mandates input validation and path sanitization that directly prevent path traversal.
Application security requirements include rules for safe file handling and canonicalization.
Secure architecture principles require least-privilege file access and directory isolation.
Secure coding standards explicitly forbid unsafe path construction and mandate safe APIs.
Information access restriction limits which files an application may read or write.