Cyber Resilience

CVE-2026-34753

SSRF in Vllm 0.16.0 – 0.19.0

SSRF
Published
06 April 2026
Modified
20 April 2026
Patch / advisory
View advisory
CVSS Score v3.1 5.4
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
EPSS Score 0.0025 16th percentile
Risk Priority 42 floored blend · peak EPSS

Summary

CVE-2026-34753 is a medium-severity SSRF (CWE-918) vulnerability in Vllm Vllm. Its CVSS base score is 5.4 (Medium).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 16th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Supply Chain and Deployment 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)

A01:2025 Broken Access Control

EU & UK References

Vulnerability Data

vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner…

more

issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions. This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.

CWE(s)
CWE-918

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Supply Chain and Deployment
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms, vllm

Related Threats

MITRE ATT&CK Enterprise Techniques

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-24779Same product: Vllm Vllm
CVE-2026-25960Same product: Vllm Vllm
CVE-2026-48746Same product: Vllm Vllm
CVE-2025-30165Same product: Vllm Vllm
CVE-2025-32444Same product: Vllm Vllm
CVE-2025-29783Same product: Vllm Vllm
CVE-2024-11041Same product: Vllm Vllm
CVE-2025-47277Same product: Vllm Vllm
CVE-2025-24357Same product: Vllm Vllm
CVE-2026-34760Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.16.0 — 0.19.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)

—

Validate
Prove the fix (OWASP ASVS)
  • V1.3.6
  • V1.5.3
  • V5.3.2
  • V10.4.7

Mitigating Controls (NIST 800-53 r5) AI

AC-4 Information Flow Enforcement good match

Information flow enforcement can restrict which destinations the server is allowed to contact on behalf of users.

SI-10 Information Input Validation good match

Input validation directly stops untrusted URLs from being accepted and fetched without destination checks.

SC-7 Boundary Protection partial match

Boundary protection limits the network reach of server-initiated requests even if SSRF occurs.

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.

PR.PS-06 mostly match
prevents

Secure development practices directly include input validation and destination allow-listing that prevent SSRF.

DE.CM-09 partial match
prevents

Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.

ID.RA-01 partial match
prevents

Vulnerability identification processes can discover and record SSRF flaws in web applications.

PR.IR-01 partial match
prevents

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.

A.5.7 Threat intelligence partial match
prevents

Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.

References