Security Digest · Vulnerability record
CVE-2025-32444: vLLM Vulnerable to Remote Code Execution via Mooncake Integration
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.
CVSS 10.0 Critical EPSS 1.8% · p78
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
- EPSS 1.8%, percentile 78: FIRST’s model estimates a 1.8% chance of exploitation activity in the next 30 days, higher than 78% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
vllm(PyPI) >= 0.6.5, < 0.8.5, fixed in 0.8.5. Check your lockfile, including transitive dependencies.
What it is
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable 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. vLLM instances that do not make use of the mooncake integration are not vulnerable. This issue has been patched in version 0.8.5.
From the GitHub advisory
Impacted Deployments
Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.
Description
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
Weakness type: CWE-502.
Product: vllm (PyPI) · Assigned by: GitHub_M · Published: 2025-04-30
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | vllm | >= 0.6.5, < 0.8.5 | 0.8.5 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| vllm-project | vllm | >= 0.6.5, < 0.8.5 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| GitHub_M | 3.1 | 10 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| GitHub | 3.1 | 10.0 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: changed (can affect other components)
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 1.79% probability of exploitation activity in the next 30 days; percentile 78.
Timeline
- — GitHub-reviewed advisory GHSA-hj4w-hm2g-p6w5 published (critical)
- — CVE record last updated
- — CVE record published by GitHub_M
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-hj4w-hm2g-p6w5 github.com
- CVE.org record CVE-2025-32444 cve.org
- NVD entry CVE-2025-32444 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com