CVE-2026-26029
Published: 11 February 2026
Summary
CVE-2026-26029 is a high-severity OS Command Injection (CWE-78) vulnerability. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked at the 8.0th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as APIs and Models; 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.
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Command injection via unsafe child_process.exec enables arbitrary shell command execution (T1059); client-side desktop app with UI:R requirement maps to exploitation for client execution (T1203).
NVD Description
sf-mcp-server is an implementation of Salesforce MCP server for Claude for Desktop. A command injection vulnerability exists in sf-mcp-server due to unsafe use of child_process.exec when constructing Salesforce CLI commands with user-controlled input. Successful exploitation allows attackers to execute arbitrary…
more
shell commands with the privileges of the MCP server process.
Deeper analysisAI
CVE-2026-26029 is a command injection vulnerability (CWE-78) in sf-mcp-server, an implementation of the Salesforce MCP server for Claude for Desktop. The flaw arises from the unsafe use of child_process.exec when constructing Salesforce CLI commands that incorporate user-controlled input, enabling attackers to inject and execute arbitrary shell commands with the privileges of the MCP server process. The vulnerability has a CVSS v3.1 base score of 7.5 (AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H), rated as high severity.
Attackers can exploit this vulnerability remotely over the network without requiring privileges, though it demands high attack complexity and user interaction, such as tricking a user into providing malicious input through the application's interface. Successful exploitation grants attackers the ability to execute arbitrary shell commands under the context of the MCP server process, potentially leading to high confidentiality, integrity, and availability impacts, including data theft, modification, or system compromise on the host running the server.
Mitigation details are available in the project's GitHub security advisories (GHSA-h4w9-g9c5-vfwq) and a related patch commit (99fba0171b8c22b5ee3c0405053ccfd2910a066d), which security practitioners should review for remediation steps, such as updating to a patched version of sf-mcp-server.
Details
- CWE(s)
AI Security AnalysisAI
- AI Category
- APIs and Models
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp, mcp, claude, mcp, mcp