Internal data disclosure via unfiltered visit_page URLs
Published Jul 21, 2026 · Updated Jul 21, 2026
SSRF in mzxrai mcp-webresearch 0.1.7 allows remote attackers to read internal HTTP services through a prompt-injected visit_page URL. The visit_page handler passes an LLM-produced URL to Playwright after isValidUrl checks only for HTTP or HTTPS, without blocking reserved addresses or redirect targets. A prompt-injected research result is sufficient to steer the browser to loopback, private, or cloud metadata endpoints and return page text, including exposed credentials, into model context.
Summary
What happened
SSRF in mzxrai mcp-webresearch 0.1.7 allows remote attackers to read internal HTTP services through a prompt-injected visit_page URL. The visit_page handler passes an LLM-produced URL to Playwright after isValidUrl checks only for HTTP or HTTPS, without blocking reserved addresses or redirect targets. A prompt-injected research result is sufficient to steer the browser to loopback, private, or cloud metadata endpoints and return page text, including exposed credentials, into model context.
The record
- CVE
- CVE-2026-65056
- Published
- Jul 21, 2026
- Updated
- Jul 21, 2026
- Vendor
- mzxrai
- Product
- mcp-webresearch
- Classifications
- CWE-918, T1552.005
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 21, 2026CVE publishedPublication date reported by the CVE source.
- Jul 21, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <=0.1.7
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- mcp-webresearch visit_page SSRF proof of conceptfunctional · validated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo