vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
CVE-2026-105760 · GHSA-58v5-2m8f-94pr · published 2026-10-05
- Severity
- Medium
- CVSS score
- 5.3
- Chance of exploitation (EPSS)
- 0.30%
- Fixed in
- 0.30.0
- Exploitation No known exploitation
- Automatable Yes
- Technical impact Partial
- CISA SSVC
The OpenAI-compatible chat endpoint accepts request-level video loader options through mediaiokwargs. A caller can select the GLMGA sampler and provide large fps and max_frames values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the supplied video contains only a few frames. This work occurs in the shared media-loading executor before frame reads, allowing a tiny valid video and compact JSON options to consume disproportionate CPU time and memory and delay unrelated media requests. The demonstrated impact is partial denial of service. No memory corruption, data disclosure, or code execution is claimed.
Upgrade vllm to 0.30.0 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.
Validate request-level video sampling options before dispatching work to the media executor. Enforce conservative absolute limits for fps, maxframes, and especially the computed candidate count. Reject non-finite, negative, or otherwise invalid numeric values. Avoid constructing O(extractt) intermediate Python lists. Generate bounded unique frame indices directly from the source frame count and output-frame limit. Apply the limit before list construction and before shared executor submission. Add tests showing that extreme request values are rejected or consume constant memory for a fixed output-frame count.
Remove or filter request-level videobackend, fps, and maxframes options at the gateway. Do not allow untrusted callers to select GLMGA. Apply authentication, rate limiting, request concurrency limits, and process memory isolation. Use a separate constrained media-loading worker pool where operationally feasible. Existing media byte, pixel, or decoded-frame limits do not necessarily bound this pre-decode candidate-index allocation.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.23.0rc2, < 0.30.0 | 0.30.0 |
- 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 (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.