vLLM Deserialization of Untrusted Data vulnerability

Mô tả

Tham khảo

• nvd.nist.gov/vuln/detail/CVE-2024-11041 · ADVISORY
• vllm-project/vllm · PACKAGE
• vllm-project/vllm · WEB
• huntr.com/bounties/00136195-11e0-4ad0-98d5-72db066e867f · WEB
• pypi.org/project/vllm · PACKAGE
• GitHub Advisory GHSA-5vqr-wprc-cpp7 · ADVISORY

Lỗ hổng khác của vllm

• CVE-2026-115918TRUNG BÌNH 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-2026-115917TRUNG BÌNH 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-2026-115916TRUNG BÌNH 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-2026-115915NGHIÊM TRỌNG 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-2026-115914TRUNG BÌNH 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…