Multimodal chat audio decoding bypasses the decompression-bomb duration limit
GHSA-r45p-7qwx-qwjw · published 2026-10-09
- Severity
- Medium
- CVSS score
- 6.5
- Chance of exploitation (EPSS)
- No CVE
- Fixed in
- 0.24.0
Medium CWE-409: Improper Handling of Highly Compressed Data (Data Amplification) An attacker who can submit chat completion requests to an audio-capable vLLM deployment can provide a small compressed audio input that expands to very large decoded PCM. The decoder accumulates decoded frames before model-level audio clip limits run, which can exhaust memory or materially degrade availability. This does not require a large request body when the payload is supplied as an audio_url, and the input_audio path is also affected for compressed audio that fits within normal request size limits. …
Upgrade vllm to 0.24.0 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.
Apply the decoder duration guard inside AudioMediaIO, not only in the speech-to-text endpoint: add a validated max_duration_s field to AudioMediaIO; default it to envs.VLLM_MAX_AUDIO_DECODE_DURATION_S; pass it from load_bytes() and load_file() into load_audio(...); prevent untrusted request-level media_io_kwargs["audio"] from disabling or raising the server-side cap beyond operator policy; add regression coverage for AudioMediaIO, MediaConnector.fetch_audio(), and chat input_audio/audio_url.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | >= 0.19.0, < 0.24.0 | 0.24.0 |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
- 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.