GHSA-x3m8-f7g5-qhm7 is a critical-severity (CVSS 9) Deserialization of Untrusted Data vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.
vLLM Allows Remote Code Execution via Mooncake Integration
Exploitation Status
No confirmed exploitation observed yet
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
- A successful exploit gives an attacker total control of the affected component, not partial access.
- CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.
Exploitation and automatability from CISA’s SSVC triage for GHSA-x3m8-f7g5-qhm7.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
How urgent is this, really
GHSA-x3m8-f7g5-qhm7 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.
Where this sits among everything scored
Of 379,842 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.
Real-World Exposure
vllmReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.
Description
Summary
When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP will allow attackers to execute remote code on distributed hosts.
Details
- Pickle deserialization vulnerabilities are well documented.
- The mooncake pipe is exposed over the network (by design to enable disaggregated prefilling across distributed environments) using ZMQ over TCP, greatly increasing exploitability.
Further, the mooncake integration opens these sockets listening on all interfaces on the host, meaning it can not be configured to only use a private, trusted network.
Only sender_socket and receiver_ack are allowed to be accessed publicly, while the data actually decompressed by pickle.loads() comes from recv_bytes. Its interface is defined as self.receiver_socket.connect(f\"tcp://{d_host}:{d_rank_offset + 1}\"), where d_host is decode_host, a locally defined address 192.168.0.139,from mooncake.json (https://github.com/kvcache-ai/Mooncake/blob/main/doc/en/vllm-integration-v0.2.md?plain=1#L36).
- The root problem is
recv_tensor()calls_recv_implwhich passes the raw network bytes topickle.loads(). Additionally, it does not appear that there are any controls (network, authentication, etc) to prevent arbitrary users from sending this payload to the affected service.
Impact
This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts.
Remediation
This issue is resolved by https://github.com/vllm-project/vllm/pull/14228
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.6.5&&< 0.8.0 | 0.8.0pip install --upgrade 'vllm==0.8.0' |
Affected Products
vllmvllmDetection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update vllm to 0.8.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms GHSA-x3m8-f7g5-qhm7 is resolved across your whole dependency graph.
Workarounds
Do not deserialise data from untrusted sources: where the format allows it, restrict deserialisation to an explicit allowlist of expected types, and prefer a data-only format (JSON, Protobuf) over one that can reconstruct arbitrary objects until you can upgrade.
Fixing This On Your OS
If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.
RHEL-AI is not affected as it does not include Mooncake, which is required for vLLM to be configured in a way that would expose this vulnerability.
A possible mitigation would be making fields transient which protect them from deserialization and helping to prevent this attack.Source: Red Hat security advisory for GHSA-x3m8-f7g5-qhm7 (CC BY 4.0)
Frequently Asked Questions
Is GHSA-x3m8-f7g5-qhm7 in your dependencies?
Find it across PyPI, including transitive dependencies.