What is the CVSS score of CVE-2026-0599?

CVE-2026-0599 has a CVSS 3.0 base score of 7.5 (High). CVSS vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H. EPSS exploitation probability: 0.1%.

Which versions of VLM are affected by CVE-2026-0599?

A vulnerability in Hugging Face text-generation-inference allows attackers to trigger uncontrolled image fetching without authentication, potentially enabling denial-of-service attacks or resource…. A patch is available.

How to fix or mitigate CVE-2026-0599?

Within 24 hours: Inventory all systems running text-generation-inference version 3.3.6 and assess exposure to untrusted networks. Within 7 days: Implement network-level restrictions to limit outbound image fetching and deploy WAF rules to restrict input sizes; disable VLM mode if operationally feasible. Within 30 days: Monitor for vendor patch availability and establish upgrade timeline; evaluate migration to alternative VLM solutions if patch timeline is unclear.

VLM CVE-2026-0599

HIGH

Uncontrolled Resource Consumption (CWE-400)

2026-02-02 security@huntr.dev

GHSA-j7x9-7j54-2v3h

Denial Of Service

7.5

CVSS 3.0 · NVD

Severity by source

NVD PRIMARY

7.5 HIGH

AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

None

Integrity

None

Availability

High

Lifecycle Timeline

Patch released

Mar 31, 2026 - 21:13 nvd

Patch available

Analysis Generated

Mar 12, 2026 - 22:01 vuln.today

CVE Published

Feb 02, 2026 - 11:16 nvd

HIGH 7.5

DescriptionCVE.org

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.

AnalysisAI

Unbounded external image fetching in Hugging Face text-generation-inference 3.3.6 VLM mode enables unauthenticated remote attackers to exhaust system resources through malicious Markdown image links in API requests. The router fetches and loads entire image files into memory during input validation regardless of subsequent token limit rejections, causing memory inflation, bandwidth saturation, and potential denial of service on unprotected deployments. This vulnerability affects default configurations lacking authentication and memory limits, with no patch currently available.

Technical ContextAI

Classified as CWE-400 (Uncontrolled Resource Consumption). Affects huggingface/text-generation-inference. A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU over