Home

Description

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 Reserved 2026-01-05 | Published 2026-02-02 | Updated 2026-02-02 | Assigner @huntr_ai




HIGH: 7.5CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Problem types

CWE-400 Uncontrolled Resource Consumption

Product status

Any version before 3.3.7
affected

References

huntr.com/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd

github.com/...ommit/24ee40d143d8d046039f12f76940a85886cbe152

cve.org (CVE-2026-0599)

nvd.nist.gov (CVE-2026-0599)

Download JSON