Skip to main content
CVE-2025-68144VulnerabilityPublished

CVE-2025-68144: modelcontextprotocol servers · Argument Injection

Affects modelcontextprotocol serversSource CVE Database V5

0

Not known to be exploited · CVSS 6.3 Medium : upgrade to 2025.12.17 when convenient.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 4.0 base score
6.3Medium
How severe the flaw is on the 0–10 CVSS scale.
EPSS
7.2% chance of exploitation in 30 days – higher than 94% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 2025.12.17
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

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 17 Dec 2025

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponised: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 2026-10-25.

What to do

Upgrade modelcontextprotocol/servers to 2025.12.17.

Affected software

ProductAffectedFixed in
GitHubmodelcontextprotocol/serverspkg:github/modelcontextprotocol/serversOther threatsAffected
  • <2025.12.17
Fixed in
  • 2025.12.17

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

European organizations should immediately plan to upgrade all affected modelcontextprotocol server instances to version 2025.12.17 or later once available. Until patching is complete, implement strict input validation and sanitization on any user inputs that interact with git commands, ensuring no arguments starting with '-' are accepted. Employ application-layer firewalls or intrusion prevention systems to detect and block suspicious command injection patterns targeting git CLI usage. Limit user permissions and isolate mcp server environments to minimize impact of potential file overwrites. Conduct security awareness training to reduce the risk of social engineering attacks that could trigger user interaction exploitation. Regularly audit git repository and server file integrity to detect unauthorized changes. Finally, monitor logs for anomalous git command executions that include unexpected flags or parameters. These targeted mitigations go beyond generic advice by focusing on the specific injection vector and operational context of the vulnerability.

Description

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.

References

Community reviews

Loading reviews…