Cyber Resilience

CVE-2025-68144

Lfprojects Model Context Protocol Servers ≤ 2025.12.17

Published
17 December 2025
Modified
14 April 2026
Patch / advisory
CVSS Score v4 6.3
Click a component to see what it means
Raw vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:N/SC:N/SI:H/SA:L/E:X/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:X
EPSS Score 0.074 94th percentile
Risk Priority 35 floored blend · peak EPSS

Summary

CVE-2025-68144 is a medium-severity Argument Injection (CWE-88) vulnerability in Lfprojects Model Context Protocol Servers. Its CVSS base score is 6.3 (Medium).

Operationally, ranked in the top 6% of CVEs by exploit likelihood; 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.

The strongest mitigations our analysis identified map to SI-10 (Information Input Validation) and SI-4 (System Monitoring) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

In mcp-server-git versions prior to 2025.12.17, the git_diff and git_checkout functions passed user-controlled arguments directly to git CLI commands without sanitization. Flag-like values (e.g., `--output=/path/to/file` for `git_diff`) would be interpreted as command-line options rather than git refs, enabling arbitrary file…

more

overwrites. The fix adds validation that rejects arguments starting with - and verifies the argument resolves to a valid git ref via rev_parse before execution. Users are advised to update to 2025.12.17 resolve this issue when it is released.

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

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

Insufficient information to map techniques.
Confidence: LOW · MITRE ATT&CK Enterprise v19.0

CVEs Like This One

CVE-2026-27735Same product: Lfprojects Model Context Protocol Servers
CVE-2025-68145Same product: Lfprojects Model Context Protocol Servers
CVE-2025-68143Same product: Lfprojects Model Context Protocol Servers
CVE-2026-27896Same vendor: Lfprojects
CVE-2026-44429Same vendor: Lfprojects
CVE-2025-66414Same vendor: Lfprojects
CVE-2026-33252Same vendor: Lfprojects
CVE-2026-52869Same vendor: Lfprojects
CVE-2026-44430Same vendor: Lfprojects
CVE-2026-34237Same vendor: Lfprojects

Affected Assets

lfprojects
model context protocol servers
≤ 2025.12.17

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)
  • SI-10 Information Input Validation
  • SI-7 Software, Firmware, and Information Integrity
Detect
Catch it (NIST detect / respond)
  • SI-7 Software, Firmware, and Information Integrity
  • SI-4 System Monitoring
Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.2.5

Mitigating Controls (NIST 800-53 r5) AI

prevent

Directly requires validation of untrusted inputs before they are passed to external commands, blocking the unsanitized flag-like arguments that enable the argument injection.

preventdetect

Requires integrity verification of inputs and outputs used by system processes, which would detect or block malformed arguments supplied to git CLI invocations.

detect

Mandates monitoring of system processes and command execution, enabling detection of anomalous git invocations containing unexpected option flags.

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 mostly match
prevents

Secure SDLC practices directly require proper input validation and command construction to prevent argument injection.

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.

detects

Security testing can detect argument injection but does not prevent it at the source.

prevents

Secure development lifecycle mandates input validation and command construction practices that directly prevent argument injection.

prevents

Application security requirements include explicit rules for safe command-line argument handling and escaping.

prevents

Secure architecture principles discourage unsafe command invocation patterns and favor safer APIs.

prevents

Secure coding standards explicitly require proper neutralization of command arguments, directly eliminating CWE-88.

none

Change management can catch unsafe command patterns during reviews but is not a direct mitigation.

References