CVE-2026-53711 MCP ContextForge: Global Prompts stored cross-site scripting compromises the Admin UI
An authenticated attacker can inject malicious scripts into Global Prompts, leading to session hijacking and data theft when other users view the Admin UI.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2026-53711?
CVE-2026-53711 is a medium-severity cross-site scripting vulnerability in IBM mcp-context-forge, published on 13 Oct 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.
Official 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.
Weakness: CWE-79
Which versions are affected by CVE-2026-53711?
How do I fix CVE-2026-53711?
No fix has been published for CVE-2026-53711 yet. Limit exposure of the affected software until one is available.
Escape output for the context it lands in and set a strict Content Security Policy. Upgrading the affected component is the real fix. More about Cross-site scripting.
Is CVE-2026-53711 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-53711 exists.
Sources
Also known as GHSA-x6gc-rm5j-55mw.