CVE-2026-53711

5.1Medium

Published 13 Oct 2026 · NVD status: Deferred · AI triage by gemini-3.8-flash

5.1Medium

Attack vector: Network
Complexity: Low
Privileges needed: Low
User interaction: Passive
Impact: Limited impact
Weakness: CWE-79

Impact

Authenticated attackers can execute arbitrary JavaScript in the browsers of users viewing Global Prompts, allowing session hijacking, phishing, or interface tampering. The attacker needs an authenticated account to save a malicious prompt, and another user must view it in the Admin UI.

Root cause

The Admin UI renders stored prompt templates in the Global Prompts feature without sufficient output encoding.

Affected systems

MCP Context Forge 0.2.0 through versions prior to 0.3.1

CVSS v4.0 · CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:L/SI:L/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Fix & remediation

Upgrade MCP Context Forge to version 0.3.1 or later. No interim workaround is documented.

AI-suggested. Run it in staging first and check it against the vendor advisory. Why?

Ad · In-content banner

NVD description

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.

References

Source: nvd.nist.gov/vuln/detail/CVE-2026-53711