CVE-2026-0599 | Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in 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 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.

Published: 2026-02-02 Last update: 2026-04-15 Assigner: [email protected] Source: [email protected]
NVD Status：Deferred，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-0599 is rated Moderate Risk (45.8/100): CVSS High severity, with low exploitation likelihood (EPSS 0.61%). Review affected assets and schedule remediation.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-0599

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-06-15 0.26% 0.61% +0.35%
2 2026-04-11 0.24% 0.26% +0.01%
3 2026-03-16 — 0.24% —

Full EPSS history (5 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-0599

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
7.5 3.0 HIGH
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:N)
Doesn’t really leak secrets in a meaningful way.
Integrity (I:N)
Data isn’t meaningfully altered or forged.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 3.6 [email protected]

Weakness enumeration for CVE-2026-0599

GitHub Security Advisory for CVE-2026-0599

GHSA-j7x9-7j54-2v3h · Severity: high · Ecosystem: pip — Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption

Affected software / configurations for CVE-2026-0599

Vendor Product Version Raw CPE
No affected products in dataset.

References for CVE-2026-0599

cvelogic Threat Intelligence