CVE-2026-0599

published 2 Feb 2026 · updated 2 Feb 2026

Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference

8.0HighCVSS 7.5EPSS 29%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 29%. Fixed in 3.3.7.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
huggingface<3.3.73.3.7

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-0599 severity on Zeptric[![CVE-2026-0599](https://zeptric.io/badge/cve/CVE-2026-0599.svg)](https://zeptric.io/cve/CVE-2026-0599)