Advisory details:
pypa / vllm/PYSEC-2026-2012
| Advisory ID | pypa/vllm/PYSEC-2026-2012 |
| Aliases |
CVE-2025-62426
GHSA-69j4-grxj-j64p PYSEC-2026-2012 |
| Summary | vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs` ### 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. https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814 https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610 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 https://github.com/vllm-project/vllm/pull/27205 |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 5.9 |
| Risk | 3.0 |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| There are no known CWE. |
| System | Score | Found at |
|---|---|---|
| cvssv3.1 | 6.5 | https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-2012.yaml |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Privileges Required (PR) | User Interaction (UI) | Scope (S) | Confidentiality Impact (C) | Integrity Impact (I) | Availability Impact (A) |
|---|---|---|---|---|---|---|---|
network adjacent_network local physical |
low high |
none low high |
none required |
unchanged changed |
high low none |
high low none |
high low none |
Vector: SSVCv2/E:N/A:N/T:P/P:M/B:A/M:M/D:T/2025-11-24T17:12:00Z/
Decision: Track
Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2025/62xxx/CVE-2025-62426.json
Source Advisory: vulnrichment/CVE-2025-62426
[{'Exploitation': 'none'},
{'Automatable': 'no'},
{'Technical Impact': 'partial'},
{'Mission Prevalence': 'minimal'},
{'Public Well-being Impact': 'material'},
{'Mission & Well-being': 'medium'}]