HighVulnerabilityLLM-specific

CVE-2026-65056: mcp-webresearch server-side request forgery in visit_page tool

Source: NVD(opens in a new tab)
Identifier: CVE-2026-65056
Published: July 21, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.3%

Summary

mcp-webresearch 0.1.7 contains a server-side request forgery vulnerability in its visit_page tool. The tool checks only the URL protocol and does not filter loopback, link-local, or cloud metadata addresses, so an attacker who steers the LLM-controlled URL argument, for example through prompt injection, can make the server's Playwright browser fetch internal endpoints and return sensitive content, including credentials, into the model context.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 8.2(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:N
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: required
EPSS: 0.3%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 13, 2026.
Disclosure date: July 21, 2026

Weaknesses and techniques

Weakness (CWE): CWE-918
Attack pattern (CAPEC): CAPEC-664
AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection,
Other
Attack sophistication: Moderate
AI component targeted: Plugin
Impact: Confidentiality
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-65056

First tracked: July 22, 2026 at 02:07 AM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 93% (self-assessed)

Summary

Mitigation

Related items