vllm: Deserialization of Untrusted Data
CVE-2025-47277 is a critical-severity deserialization of untrusted data vulnerability in vllm from Vllm-project, with a CVSS 3.1 base score of 9.8 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. Affected vllm versions: >= 0.6.5, < 0.8.5. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 0.96% chance of exploitation within 30 days, higher than 62% of scored CVEs.
Critical severity: a successful attack would have severe impact.
What to do
- Check which version of vllm you run against the affected versions below, and install the vendor's latest release.
- Read the advisory on github.com for workarounds and exact fixed builds.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Vllm-project | vllm | >= 0.6.5, < 0.8.5 | Not stated |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- UnchangedImpact stays within the vulnerable component.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H. Scored by CNA (github.com).
Official 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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Deserialization of Untrusted Data
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
How developers prevent this class of flaw
- If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
- When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
- Explicitly define a final object() to prevent deserialization.
More Deserialization of Untrusted Data vulnerabilities (CWE-502)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: yes, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Advisories
Patches and release notes
Other references
- docs.vllm.ai/en/latest/deployment/security.htmlTechnical Description
Other vulnerabilities in vllm
- 7.5 High severity
- 9.8 Critical severity
- 8.8 High severity
- 7.7 High severity
- 7.5 High severity
- 7.5 High severity
Recent Deserialization of Untrusted Data vulnerabilities
- 9.8 Critical severity
- 9.8 Critical severity
- 9.8 Critical severity
- 9.8 Critical severity
- 9.8 Critical severity
- 9.8 Critical severity
Spotted an error? Tell us.