Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption
CVE-2026-0599 · GHSA-j7x9-7j54-2v3h · published 2026-02-02
- Severity
- High
- CVSS score
- 7.5
- Chance of exploitation (EPSS)
- 29.5%
- Fixed in
- 3.3.7
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
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.
Upgrade text-generation to 3.3.7 or later.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| text-generation | PyPI | < 3.3.7 | 3.3.7 |
- HightsParticles: Unbounded HTTP Request Body Buffering in @tsparticles/mcp-server Leads to Remote DoS@tsparticles/mcp-server
- HighMissing request-wide media budget allows single-request frontend resource exhaustionvllm
- HighMCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length@modelcontextprotocol/hono, @modelcontextprotocol/node, @modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighvLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)vllm
- HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighFrame-count cap bypass in VideoMediaIO.load_base64 for video/jpeg via media_io_kwargs.video.num_framesvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.