CVE-2025-63603 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 functio...
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: yes · technical impact: total
Description
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.
Upgrade path
1 package: 0 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| mcp server for data exploration project mcp server for data exploration | = 0.1.6 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| mcp server for data exploration project mcp server for data exploration | = 0.1.6 | No fix listed |
References
- github.com exploit issue-tracking third-party-advisory