CVE-2025-32444Critical· 10.0▾ MidnightvLLM Vulnerable to Remote Code Execution via Mooncake Integration
▾ Midnight zone — Critical, or high with PoC / in-the-wild
impact 55 · likelihood 0.4 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Aug 7.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
1.7%
1.7% → 1.8%
Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.
vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack.
This is a similar to GHSA - x3m8 - f7g5 - qhm7, the problem is in
Here recv_pyobj() Contains implicit pickle.loads(), which leads to potential RCE.
vllm >= 0.6.5, < 0.8.5Upgrade to a patched release:
vllm 0.8.5Connected by shared product, vendor, weakness, or advisory.
CVE-2025-29783Critical· 9.0vLLM Allows Remote Code Execution via Mooncake Integration
CVE-2026-115911Medium· 6.5vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
CVE-2026-115912High· 7.5vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
CVE-2026-115913Medium· 6.5vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
CVE-2026-115916Medium· 6.5vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
CVE-2026-115917Low· 3.4vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server