cve.bz

CVE-2025-68144 lfprojects model context protocol servers: Argument Injection

6.3 mediumEPSS 7.7%Fix available

Medium (6.3) in lfprojects model context protocol servers. EPSS 7.7% estimated probability of exploitation activity in the next 30 days. Fixed in mcp-server-git 2025.12.18.

On this page
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 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.

Severity

CVSS 4.0

6.3 medium
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:N/SC:N/SI:H/SA:L

CVSS 3.1

7.1 high
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:L
EPSS
7.7% (unchanged from 7.2% a week ago; 7.2% 30 days ago) estimated probability of exploitation activity in the next 30 days; 95th percentile. Scored 2026-11-22. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: partial, assessed 2025-12-18. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-88 Improper Neutralization of Argument Delimiters in a Command (Argument Injection)
OWASP Top 10
A05:2025 Injection
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2025-68144 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2025-68144?via=ask-ai-copy and https://cve.bz/cve/CVE-2025-68144?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2025-68144 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the NVD's CPE matches.

ProductAffected
lfprojects:model_context_protocol_serversbefore 2025.12.17

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-9xwc-hfwc-8w59PyPImcp-server-git<2025.12.182025.12.18
PYSEC-2026-1622PyPImcp-server-git<2025.12.182025.12.18

Attack patterns (CAPEC)

  • CAPEC-41 Using Meta-characters in E-mail Headers to Inject Malicious Payloads Likelihood: High · Severity: High
  • CAPEC-88 OS Command Injection Likelihood: High · Severity: High
  • CAPEC-137 Parameter Injection Likelihood: Medium · Severity: Medium
  • CAPEC-174 Flash Parameter Injection Likelihood: High · Severity: Medium
  • CAPEC-460 HTTP Parameter Pollution (HPP) Severity: Medium

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON