Vulnerabilities in Inference & serving
Model servers, runtimes and LLM gateways. 34 currently disclosed, newest first. Each links through to the merged record for that CVE.
- 8.1 vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
- 8.1 LiteLLM: internal_user_viewer arbitrary local file read via `vertex_ai_credentials`
- 6.8 LiteLLM vulnerable to reflected XSS in /sso/debug/callback
- 7.7 LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key
- 6.5 vllm p2p never connected zmq_exhaustion
- 6.9 llama.cpp b5854 before b11275 contains an integer overflow vulnerability in ggufinitfromreader that bypasses the CVE-2025-53630 size check…
- 6.9 llama.cpp b10398 before b11301 contains an integer overflow vulnerability in ggufinitfromreader that allows attackers to bypass tensor…
- 8.5 llama.cpp b5899 before b10261 contains a heap out-of-bounds write vulnerability in llmtokenizerplamo2::build that allows attackers to…
- 6.8 llama.cpp before b5649 contains a heap out-of-bounds read vulnerability in llamavocab::impl::printinfo() that allows attackers to crash…
- 8.8 llama.cpp before b3701 contains an out-of-bounds read vulnerability in llamadecodeinternal and llamaencodeinternal that allows remote…
- 6.9 llama.cpp before b2731 contains an out-of-bounds read vulnerability in llamamodelloader that allows attackers to read memory outside the…
- 6.9 A security flaw has been discovered in ggml-org llama.cpp up to 0.7.0.
- 6.5 vLLM is an inference and serving engine for large language models.
- 4.7 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 9.8 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 8.8 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 1.9 A weakness has been identified in ggml-org llama.cpp.
- 7.1 vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by…
- 8.3 vLLM from 0.8.5 before 0.31.0 has a denial of service flaw.
- 8.7 vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count…
- 8.2 vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending…
- 8.7 vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust…
- 8.8 vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by…
- 7.1 vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls loadaudio without…
- 8.2 vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream service…
- 8.2 vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing…
- 8.2 vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers…
- 7.5 vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)
- 6.5 vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine
- — BerriAI LiteLLM Improper Authentication Vulnerability
Open this in the live dashboard
to filter further, or query it with search_cves over MCP.