vllm has Improper Resource Shutdown or Release

Description

References

• nvd.nist.gov/vuln/detail/CVE-2026-9540 · ADVISORY
• vllm-project/vllm · WEB
• vllm-project/vllm#37594 · WEB
• vllm-project/vllm · PACKAGE
• ingero.io/debugging-vllm-latency-minimax-ollama-mcp · WEB
• vuldb.com/submit/814645 · WEB
• vuldb.com/vuln/365601 · WEB
• vuldb.com/vuln/365601/cti · WEB
• vllm-project/vllm
• ingero.io/debugging-vllm-latency-minimax-ollama-mcp
• pypi.org/project/vllm · PACKAGE
• GitHub Advisory GHSA-98f3-hwg4-4rf7 · ADVISORY

vllm의 다른 취약점

• CVE-2026-115918보통 6.5vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authentica…
• CVE-2026-115917보통 4.7vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMi…
• CVE-2026-115916보통 6.5vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-…
• CVE-2026-115915심각 9.8vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to P…
• CVE-2026-115914보통 6.5vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited…