MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server

published 2026-08-24 2 mo ago modified 2026-09-30 39 d ago also GHSA-xm98-3vcf-fph7 , PYSEC-2026-3862 , EUVD-2026-78933

cvss: 10.0; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 1.1%; EPSS 1.1% chance of exploitation in 30 days, percentile 66%
public exploits: 0; none known

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.

Patch / fix

fixed in 1 links 2

pypi mcp-contextforge-gateway 1.0.2

CISA SSVC

Exploitation: none
Automatable: yes
Technical impact: total
Assessed: 54 d ago (2026-09-15)

Exploit prediction

1.14% chance of exploitation in the next 30 days, higher than 66% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	3.1	10.0	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
GitHub	3.1	10.0	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H
OSV	3.1	10.0	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Affected packages

ecosystem	package	affected	fixed in
pypi	mcp-contextforge-gateway	<1.0.2	1.0.2

Affected products

IBM mcp-context-forge

Classification

Weakness

CWE-94 Improper Control of Generation of Code
CWE-693 Protection Mechanism Failure

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

Summary