CVE-2026-53710: CWE-94: Improper Control of Generation of Code ('Code Injection') in IBM mcp-context-forge
CVE-2026-53710 is a critical code injection vulnerability in IBM mcp-context-forge's python_sandbox_server component prior to version 1.0.2. The flaw allows attackers to bypass safeguards and execute arbitrary OS commands with server process privileges via the execute_code MCP tool exposed over HTTP/SSE without authentication. This vulnerability does not affect the core Context Forge gateway or proxy components and is fixed in version 1.0.2.
AI Analysis
Technical Summary
IBM mcp-context-forge versions before 1.0.2 contain a code injection vulnerability in the python_sandbox_server subproject. The server exposes raw getattr through safe_builtins without the required _getattr_ guard and relies on insufficient validate_code checks for dangerous dunder strings. Attackers can dynamically construct dunder names to traverse the Python class hierarchy, reach subprocess.Popen, and execute arbitrary OS commands with the privileges of the server process via the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, increasing the attack surface. The issue is resolved in version 1.0.2.
Potential Impact
Successful exploitation allows unauthenticated remote attackers to execute arbitrary operating system commands with the privileges of the python_sandbox_server process. This can lead to full system compromise, data loss, or disruption of service. The vulnerability affects only the python_sandbox_server subproject and not the core gateway or proxy components.
Mitigation Recommendations
Upgrade to IBM mcp-context-forge version 1.0.2 or later, where this vulnerability is fixed. Until upgrading, restrict network access to the python_sandbox_server, especially the HTTP/SSE transport, to trusted users only. No other official mitigations are documented.
CVE-2026-53710: CWE-94: Improper Control of Generation of Code ('Code Injection') in IBM mcp-context-forge
Description
CVE-2026-53710 is a critical code injection vulnerability in IBM mcp-context-forge's python_sandbox_server component prior to version 1.0.2. The flaw allows attackers to bypass safeguards and execute arbitrary OS commands with server process privileges via the execute_code MCP tool exposed over HTTP/SSE without authentication. This vulnerability does not affect the core Context Forge gateway or proxy components and is fixed in version 1.0.2.
CVSS v3.1
Score 10.0critical
Affected software
IBM
mcp-context-forge
pkg:github/ibm/mcp-context-forgeRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
IBM mcp-context-forge versions before 1.0.2 contain a code injection vulnerability in the python_sandbox_server subproject. The server exposes raw getattr through safe_builtins without the required _getattr_ guard and relies on insufficient validate_code checks for dangerous dunder strings. Attackers can dynamically construct dunder names to traverse the Python class hierarchy, reach subprocess.Popen, and execute arbitrary OS commands with the privileges of the server process via the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, increasing the attack surface. The issue is resolved in version 1.0.2.
Potential Impact
Successful exploitation allows unauthenticated remote attackers to execute arbitrary operating system commands with the privileges of the python_sandbox_server process. This can lead to full system compromise, data loss, or disruption of service. The vulnerability affects only the python_sandbox_server subproject and not the core gateway or proxy components.
Mitigation Recommendations
Upgrade to IBM mcp-context-forge version 1.0.2 or later, where this vulnerability is fixed. Until upgrading, restrict network access to the python_sandbox_server, especially the HTTP/SSE transport, to trusted users only. No other official mitigations are documented.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-06-10T16:43:31.241Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6aa97a1355bf5e2cf51ed0a6
Added to database: 09/15/2026, 17:02:11 UTC
Last enriched: 09/15/2026, 17:16:37 UTC
Last updated: 09/15/2026, 17:36:58 UTC
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.