Nemotron-VL processors disable Pillow decompression-bomb guard globally, enabling unauthenticated DoS
GHSA-mm38-5g96-7j6x · published 2026-10-09
- Severity
- High
- CVSS score
- Not scored
- Chance of exploitation (EPSS)
- No CVE
- Fixed in
- 0.25.0
A deployment serving a Nemotron-VL model, or one that imports either processor, can be exposed to memory exhaustion through attacker-controlled image input. Since the setting is process-global, unrelated image loads in the same process are affected too. CWE-400 (Uncontrolled Resource Consumption).
Upgrade vllm to 0.25.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
PR #47010 removes both module-level Image.MAX_IMAGE_PIXELS = None assignments. It also adds a decoded pixel-count limit in the shared image loader, configurable through VLLM_MAX_IMAGE_PIXELS.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | <= 0.8.5 | 0.25.0 |
- HightsParticles: Unbounded HTTP Request Body Buffering in @tsparticles/mcp-server Leads to Remote DoS@tsparticles/mcp-server
- 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
- HighMCP TypeScript SDK: One HTTP request within the default size limit could exhaust server memory during validation@modelcontextprotocol/sdk, @modelcontextprotocol/server
- HighHTTP server transports and OAuth endpoints read request bodies with no size limitmcp, mcp
- HighLMDeploy vulnerable to arbitrary code execution via eval() of untrusted quant_dtype in model config loadinglmdeploy
- HighRMCP: Unauthenticated permanent session-table leak in rmcp Streamable HTTP server transport leads to remote denial-of-servicermcp
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
The impact, patch and workaround text comes from the advisory, shortened (published by vLLM). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.