CVE-2026-65056

Affects: prompt injection

CVSS
HIGH · 8.2v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:N
Published
2026-07-21
Weakness
CWE-918
Source
nvd.nist.gov/vuln/detail/CVE-2026-65056

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.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-65056 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming