CVE-2025-62426 is a medium-severity (CVSS 6.5) CWE-770 vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.
vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
Exploitation Status
No confirmed exploitation observed yet
- 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-2025-62426.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
How urgent is this, really
Where this sits among everything scored
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
The /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests
Details
In serving_engine.py, the chat_template_kwargs are unpacked into kwargs passed to chat_utils.py apply_hf_chat_template with no validation on the keys or values in that chat_template_kwargs dict. This means they can be used to override optional parameters in the apply_hf_chat_template method, such as tokenize, changing its default from False to True.
Both serving_chat.py and serving_tokenization.py call into this _preprocess_chat method of serving_engine.py and they both pass in chat_template_kwargs.
So, a chat_template_kwargs like {"tokenize": True} makes tokenization happen as part of applying the chat template, even though that is not expected. Tokenization is a blocking operation, and with sufficiently large input can block the API server's event loop, which blocks handling of all other requests until this tokenization is complete.
This optional tokenize parameter to apply_hf_chat_template does not appear to be used, so one option would be to just hard-code that to always be False instead of allowing it to be optionally overridden by callers. A better option may be to not pass chat_template_kwargs as unpacked kwargs but instead as a dict, and only unpack them after the logic in apply_hf_chat_template that resolves the kwargs against the chat template.
Impact
Any authenticated user can cause a denial of service to a vLLM server with Chat Completion or Tokenize requests.
Fix
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 🐍PyPI | vllm | ≥ 0.5.5&&< 0.11.1 | 0.11.1pip install --upgrade 'vllm==0.11.1' |
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 0.11.1 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2025-62426 is resolved across your whole dependency graph.
Workarounds
Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.
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.
The flaw is limited to a denial-of-service vector that requires an authenticated user and relies on abusing an optional, non-security-critical parameter (chat_template_kwargs) to force unexpected tokenization during template application, which is computationally expensive but not indicative of data corruption,…
No mitigation is currently available that meets Red Hat Product Security’s standards for usability, deployment, applicability, or stability.Source: Red Hat security advisory for CVE-2025-62426 (CC BY 4.0)
| Product | Fixed in | Advisory |
|---|---|---|
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-cuda-rhel9:1772160593 | RHSA-2026:3461 |
| Red Hat AI Inference Server 3.2 | rhaiis/vllm-rocm-rhel9:1772160625 | RHSA-2026:3462 |
Frequently Asked Questions
Is CVE-2025-62426 in your dependencies?
Find it across PyPI, including transitive dependencies.