CVE-2026-7811
Published: 05 May 2026
Summary
CVE-2026-7811 is a high-severity Path Traversal (CWE-22) vulnerability. Its CVSS base score is 7.3 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 14.1th 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 Protocol-Specific Risks risk domain.
Threat & Defense at a Glance
Threat & Defense Details
Likely Mitigating ControlsAI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Validates pathnames and filenames to prevent traversal outside intended directories.
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Path traversal in remotely accessible MCP File Handler directly enables T1190 for initial access; bypassed is_safe_path allows unauthorized local file read (T1005) and write (T1105) operations.
NVD Description
A vulnerability has been found in 54yyyu code-mcp up to 4cfc4643541a110c906d93635b391bf7e357f4a8. The affected element is the function is_safe_path of the file src/code_mcp/server.py of the component MCP File Handler. Such manipulation leads to path traversal. It is possible to launch the…
more
attack remotely. The exploit has been disclosed to the public and may be used. This product takes the approach of rolling releases to provide continious delivery. Therefore, version details for affected and updated releases are not available. The project was informed of the problem early through an issue report but has not responded yet.
Deeper analysisAI
CVE-2026-7811 is a path traversal vulnerability in the 54yyyu code-mcp project up to commit 4cfc4643541a110c906d93635b391bf7e357f4a8. The issue affects the is_safe_path function within the src/code_mcp/server.py file of the MCP File Handler component. Manipulation of this function enables improper path validation, allowing attackers to access unintended files or directories outside the intended scope.
The vulnerability can be exploited remotely by unauthenticated attackers with network access, requiring low complexity and no user interaction, as indicated by its CVSS v3.1 base score of 7.3 (AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L). Successful exploitation grants limited impact on confidentiality, integrity, and availability, potentially allowing read/write access to files or minor disruption via traversed paths.
Advisories from VulDB and the project's GitHub repository note that code-mcp follows a rolling release model, providing no specific affected or patched version details. The project was notified early via GitHub issue #4 but has not yet responded or issued mitigations. Security practitioners should monitor the repository at https://github.com/54yyyu/code-mcp/ for updates.
The exploit has been publicly disclosed and may be actively used, classified under CWE-22. No evidence of widespread real-world exploitation is available in current references.
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, mcp