Raw vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:L/VA:N/SC:H/SI:L/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-65056 is a high-severity SSRF (CWE-918) vulnerability in Npmjs (inferred from references). Its CVSS base score is 8.3 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 14th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
The strongest mitigations our analysis identified map to AC-4 (Information Flow Enforcement) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-46421
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp, llm, prompt injection
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
SSRF in public-facing tool directly enables T1190; explicit targeting of cloud metadata APIs for credential theft maps to T1552.005.
Likely ATT&CK TechniquesAI
Techniques this vulnerability likely enables, inferred from its description, weakness type, and attributed-actor tradecraft. Confidence is per-technique.
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
Mitigating Controls (NIST 800-53 r5) AI
Directly requires validation of URL inputs to reject private, loopback, link-local, and metadata service addresses before the visit_page tool processes them.
Enforces information flow policies that block requests from the Playwright browser to internal or reserved IP ranges, stopping SSRF to cloud metadata endpoints.
Implements boundary controls that can deny outbound connections from the server to internal network services and instance metadata addresses.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices directly include input validation and destination allow-listing that prevent SSRF.
Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.
Vulnerability identification processes can discover and record SSRF flaws in web applications.
Network segmentation and egress controls can limit the damage from successful SSRF requests.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.