Skip to content
LLMHigh

CVE-2026-65056: mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability that allows attackers to …

Occurred
Jul 21, 2026
Published
Jul 21, 2026
Source
NVD CVE

Summary

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.

Tags

  • CVE
  • CVE-2026-65056
  • cvss:HIGH

Classification

Category confidence: 90%
Severity confidence: 85%

Rationale: Vulnerability allows attackers to use prompt injection to access internal network services via LLM-controlled tool, exposing sensitive data.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source