Browse / Unbounded Consumption / CVE-2026-0599
Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption
- Class
- Unbounded Consumption (filed by a model that read the advisory)
- Technique
- Denial of service
- Affected
- text-generation (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 29.5% chance of exploitation in 30 days
How it works, in short
Remote image links in prompts are fetched in full and buffered in memory during validation, even when the request is later rejected for size. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-0599
- https://github.com/huggingface/text-generation-inference/commit/24ee40d143d8d046039f12f76940a85886cbe152
- https://github.com/huggingface/text-generation-inference
- https://huntr.com/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd
Source: GitHub Advisory Database, used under CC BY 4.0.