CVE-2026-53711

Published: Ott 13, 2026 Last Modified: Ott 13, 2026
ExploitDB:
Other exploit source:
Google Dorks:
MEDIUM 5,1
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: low
User Interaction: passive
Confidentiality: N/A
Integrity: N/A
Availability: N/A

Description

AI Translation Available

MCP Context Forge provides an MCP Admin UI for managing gateway resources. From 0.2.0 until 0.3.1, the Global Prompts feature stores a prompt template without sufficient output encoding before the MCP Admin UI renders it. An authenticated attacker can save markup containing script-capable event handlers, and the code executes when another user views the saved prompt. The stored cross-site scripting can alter the interface, present phishing content, observe keystrokes available to the page, and act with the viewer's browser session. This issue is fixed in version 0.3.1.

79

Improper Neutralization of Input During Web Page Generation ('Cross-site Scripting')

Stable
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Access Control Confidentiality Integrity Availability
Potential Impacts:
Bypass Protection Mechanism Read Application Data Execute Unauthorized Code Or Commands
Applicable Platforms
Technologies: AI/ML, Web Based, Web Server
Likelihood of Exploit: High
View CWE Details
https://github.com/IBM/mcp-context-forge/commit/acd16196158…
https://github.com/IBM/mcp-context-forge/commit/acd16196158f9a393187551b21a2fc6…
https://github.com/IBM/mcp-context-forge/pull/337
https://github.com/IBM/mcp-context-forge/pull/337
https://github.com/IBM/mcp-context-forge/releases/tag/v0.3.1
https://github.com/IBM/mcp-context-forge/releases/tag/v0.3.1
https://github.com/IBM/mcp-context-forge/security/advisorie…
https://github.com/IBM/mcp-context-forge/security/advisories/GHSA-x6gc-rm5j-55mw