reading-plus-ai mcp-server-data-exploration 0.1.6 server.py safe_eval command injection

Summaryinfo

A vulnerability marked as critical has been reported in reading-plus-ai mcp-server-data-exploration 0.1.6. Affected by this vulnerability is the function safe_eval of the file src/mcp_server_ds/server.py. Performing a manipulation results in command injection. This vulnerability is known as CVE-2025-63603. No exploit is available.

Detailsinfo

A vulnerability, which was classified as critical, was found in reading-plus-ai mcp-server-data-exploration 0.1.6. This affects the function safe_eval of the file src/mcp_server_ds/server.py. The manipulation with an unknown input leads to a command injection vulnerability. CWE is classifying the issue as CWE-77. The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

A command injection vulnerability exists in the MCP Data Science Server's (reading-plus-ai/mcp-server-data-exploration) 0.1.6 in the safe_eval() function (src/mcp_server_ds/server.py:108). The function uses Python's exec() to execute user-supplied scripts but fails to restrict the __builtins__ dictionary in the globals parameter. When __builtins__ is not explicitly defined, Python automatically provides access to all built-in functions including __import__, exec, eval, and open. This allows an attacker to execute arbitrary Python code with full system privileges, leading to complete system compromise. The vulnerability can be exploited by submitting a malicious script to the run_script tool, requiring no authentication or special privileges.

The advisory is shared at github.com. This vulnerability is uniquely identified as CVE-2025-63603 since 10/27/2025. The exploitability is told to be easy. No form of authentication is needed for exploitation. Technical details are known, but no exploit is available. The price for an exploit might be around USD $0-$5k at the moment (estimation calculated on 11/18/2025). MITRE ATT&CK project uses the attack technique T1202 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• reading-plus-ai

Name

• mcp-server-data-exploration

Version

• 0.1.6

Website

• Product: https://github.com/reading-plus-ai/mcp-server-data-exploration/

CPE 2.3info

• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion