CVE-2025-47277 is a critical-severity (CVSS 9.8) 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 PyNcclPipe Communication Service
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 CVE-2025-47277.
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
How urgent is this, really
CVE-2025-47277 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.
Where this sits among everything scored
Of 377,166 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.
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
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the PyNcclCommunicator class, while CPU-side control message passing is handled via the send_obj and recv_obj methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the --kv-ip CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the TCPStore interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the TCPStore instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the TCPStore socket to the private interface as configured.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.6.5&&< 0.8.5 | 0.8.5pip install --upgrade 'vllm==0.8.5' |
Detection & 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 0.8.5 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-47277 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.
How O3 protects you
O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2025-47277 can be triaged on real exposure rather than presence alone.
Tailored to CVE-2025-47277. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
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.
By default, Red Hat products are configured to restrict vLLM nodes to an isolated network. However, this vulnerability could become relevant if customers change the specific configurations, and therefore, Red Hat products are affected. This vulnerability is classified as Moderate rather than Critical because its…
| Product | Fixed in | Advisory |
|---|---|---|
| Red Hat AI Inference Server 3.1 | rhaiis/vllm-rocm-rhel9:3.1.0-1751522540 | RHSA-2025:10403 |
| Red Hat AI Inference Server 3.1 | rhaiis/vllm-cuda-rhel9:3.1.0-1751522544 | RHSA-2025:10404 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/instructlab-nvidia-rhel9:1.5.3-1756791365 | RHSA-2025:15832 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-intel-rhel9:1.5.3-1756724193 | RHSA-2025:15836 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-gcp-nvidia-rhel9:1.5.3-1756815294 | RHSA-2025:15837 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-aws-nvidia-rhel9:1.5.3-1756815228 | RHSA-2025:15838 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-amd-rhel9:1.5.3-1756800437 | RHSA-2025:15839 |
| Red Hat Enterprise Linux AI 1.5 | rhelai1/bootc-azure-amd-rhel9:1.5.3-1756815221 | RHSA-2025:15840 |
Frequently Asked Questions
Is CVE-2025-47277 in your dependencies?
O3 Security finds CVE-2025-47277 across PyPI dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.