Resource exhaustion in Huggingface Huggingface/text-Generation-Inference
CVE-2026-0599
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.
Vulnerability class: DoS (Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 7.5 (High). Vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.282 (98.1th percentile), scored .
Moderate probability of exploitation in the next 30 days — watch for active exploitation reports. 98th percentile — 98.1% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.225 · newest: 0.282 · change: +0.057
Affected products
- Huggingface Huggingface/text-Generation-Inference — versions unspecified
Weakness classification (CWE)
References
Frequently asked questions
- What is CVE-2026-0599?
- CVE-2026-0599 is a high-severity vulnerability in Huggingface Huggingface/text-Generation-Inference, classified under Uncontrolled Resource Consumption. CVSS score: 7.5/10. Published 2026-02-02.
- How severe is CVE-2026-0599?
- High severity. CVSS v3 base score is 7.5 out of 10.