CVE-2026-65056

Received Received - Intake

Server-Side Request Forgery in mcp-webresearch via Playwright URL Handling

Publication date: 2026-07-21

Last updated on: 2026-07-21

Assigner: VulnCheck

Description

mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability that allows attackers to access internal network services by supplying loopback, link-local, or cloud metadata addresses to the visit_page tool, which only validates the URL protocol without filtering private or reserved IP ranges. Attackers can steer the LLM-controlled URL argument through prompt injection to navigate the server's Playwright browser to internal endpoints such as cloud instance metadata services, causing the server to return sensitive internal page content including credentials into the model context.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published

2026-07-21

Last Modified

2026-07-21

Generated

2026-07-22

AI Q&A

2026-07-22

EPSS Evaluated

N/A

NVD

CVE-2026-65056

Affected Vendors & Products

Currently, no data is known.

Helpful Resources

Exploitability

CWE

KEV

CWE ID	Description
CWE-918	The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

Executive Summary

This vulnerability is a server-side request forgery (SSRF) in mcp-webresearch 0.1.7. It allows attackers to access internal network services by providing loopback, link-local, or cloud metadata addresses to the visit_page tool. The tool only checks the URL protocol but does not filter private or reserved IP ranges. Attackers can manipulate the LLM-controlled URL through prompt injection to direct the server's Playwright browser to internal endpoints like cloud instance metadata services. This causes the server to return sensitive internal page content, including credentials, into the model context.

Impact Analysis

This vulnerability can lead to unauthorized access to internal network services and sensitive data. Attackers may steal credentials or other confidential information by tricking the server into accessing internal endpoints. This could result in data breaches, unauthorized system access, or further exploitation of internal resources.

Compliance Impact

This vulnerability can lead to non-compliance with GDPR, HIPAA, and other regulations due to unauthorized access to sensitive data. GDPR requires protection of personal data, while HIPAA mandates safeguards for protected health information. A breach could result in legal penalties, fines, and reputational damage.

Mitigation Strategies

Update mcp-webresearch to a patched version that filters private or reserved IP ranges in URLs. Restrict network access to cloud metadata services and internal endpoints. Monitor network traffic for unusual requests to loopback or link-local addresses.

Hi! I’m here to help you understand CVE-2026-65056. Ask me anything about the vulnerability, its impact, or mitigation strategies.

0/70