Unbounded External Image Fetch in Validation Leads to Resource-Exhaustion DoS in huggingface/text-generation-inference
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
| Vendor | Product | Versions | Fixed |
|---|---|---|---|
| huggingface | <3.3.7 | 3.3.7 |
Timeline
Every event on this vulnerability
Embed
A live severity badge for an advisory, README or ticket