CVE-2026-53710
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
Summary
MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required getattr guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while stdio-only deployments have reduced network reachability. The issue affects the python_sandbox_server subproject and does not directly affect the core Context Forge gateway or proxy components. This issue is fixed in version 1.0.2.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| IBM | mcp-context-forge | < 1.0.2 | affected |
Weaknesses
- CWE-94: CWE-94: Improper Control of Generation of Code ('Code Injection')
- CWE-693: CWE-693: Protection Mechanism Failure
ADP Enrichment
CISA ADP Vulnrichment
- SSVC:
- Exploitation: none
- Automatable: yes
- Technical Impact: total
References
- https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-xm98-3vcf-fph7
- https://github.com/IBM/mcp-context-forge/commit/63a2900e6301b9c8a483a38d3737a1beb3a7ce89
- https://github.com/IBM/mcp-context-forge/releases/tag/v1.0.2
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.