Raw vector
CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:HSummary
CVE-2025-64340 is a medium-severity OS Command Injection (CWE-78) vulnerability in Jlowin Fastmcp. Its CVSS base score is 6.7 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Command and Scripting Interpreter (T1059); ranked in the top 49% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
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 SA-11 (Developer Testing and Evaluation) 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-2025-64340 is a command injection vulnerability (CWE-78) in FastMCP, the standard framework for building MCP applications, affecting versions prior to 3.2.0. The flaw occurs on Windows when server names containing shell metacharacters, such as &, are passed to the fastmcp install claude-code or fastmcp install gemini-cli commands. These commands invoke subprocess.run() with a list argument, but the target CLIs often resolve to .cmd wrappers executed through cmd.exe, which interprets metacharacters in the resulting flattened command string.
Exploitation requires local access, high attack complexity, low privileges, and user interaction, as indicated by the CVSS v3.1 base score of 6.7 (AV:L/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H). A low-privileged local attacker could trick a user into running one of the vulnerable install commands with a specially crafted server name containing shell metacharacters, enabling arbitrary command execution on the target Windows system with high impacts to confidentiality, integrity, and availability.
The vulnerability has been addressed in FastMCP version 3.2.0. Security advisories and the patching pull request provide further details on the fix, available at https://github.com/PrefectHQ/fastmcp/pull/3522 and https://github.com/PrefectHQ/fastmcp/security/advisories/GHSA-m8x7-r2rg-vh5g.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-209207
Vulnerability Data
FastMCP is the standard framework for building MCP applications. Prior to version 3.2.0, server names containing shell metacharacters (e.g., &) can cause command injection on Windows when passed to fastmcp install claude-code or fastmcp install gemini-cli. These install paths use…
more
subprocess.run() with a list argument, but on Windows the target CLIs often resolve to .cmd wrappers that are executed through cmd.exe, which interprets metacharacters in the flattened command string. This issue has been patched in version 3.2.0.
- 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: claude, gemini, mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
—
V1.2.5V1.2.8V15.2.5
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation can discover missing or incorrect command sanitization during development.
Input validation directly neutralizes or rejects special characters that would otherwise alter OS command structure.
Least privilege reduces the permissions available to any process that could be subverted by injected commands.
Least functionality restricts available OS commands and interpreters, limiting the blast radius of injection.
Secure engineering principles require proper neutralization of untrusted input before command construction.
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.
PR.PS-06's SDLC practices directly require secure coding and input handling that blocks command-injection defects, yet the single broad outcome leaves many specific neutralization vectors and verification gaps unaddressed.
Routine patching/maintenance can remediate known command-injection CVEs in dependencies (partial forward) but does nothing to stop developers from introducing improper neutralization in custom code (none reverse).
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 and code review target insecure use of operating-system command interfaces, catching command-injection flaws introduced during development.