Unsafe Deserialization in vllm (CVE-2025-29783)
Summary
Vulnerability in vllm (CVE-2025-29783). Successful exploitation can lead to full system takeover. Exploitable via sender_socket. Mitigation: upgrade to 0.8.0 or later.
Original description
The description as published by the source.
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.
Source: OSV.dev (Open Source Vulnerabilities) NVD GitHub Advisory OSV
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2025-29783 has been found in vllm.
Attackers can target a specific entry point like sender_socket over the network to misuse the product.
Successful exploitation can lead to full system takeover.
What to do: upgrade vllm to 0.8.0 or later.
If unsure, ask your IT team or search "vllm CVE-2025-29783" on the vendor's site.
CVE-2025-29783 (vllm) — CWE-502
Attack vector: adjacent-network / no user interaction
Attack surface: sender_socket / receiver_ack / d_host / decode_host
Patched: 0.8.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Unsafe deserialization (CWE-502) exists in vllm. Attackers reach the vulnerable code path via sender_socket.
Check the vendor advisory for the affected versions of vllm. Attack surface: sender_socket / receiver_ack / d_host / decode_host.
Severity: ?. Successful exploitation can lead to full system takeover.
Update to 0.8.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'vllm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
vllmを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade vllm to 0.8.0ステージング環境で 0.8.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory github.com
- package github.com
- patch github.com
- patch github.com
- web github.com