{"id":"PYSEC-2026-2012","summary":"vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`","details":"### Summary\nThe /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 \n\n### Details\nIn 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.\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814\n\nhttps://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610\n\nBoth 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`.\n\nSo, 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.\n\nThis 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.\n\n### Impact\n\nAny authenticated user can cause a denial of service to a vLLM server with Chat Completion or Tokenize requests.\n\n### Fix\n\nhttps://github.com/vllm-project/vllm/pull/27205","aliases":["CVE-2025-62426","GHSA-69j4-grxj-j64p"],"modified":"2026-07-07T17:47:19.712741583Z","published":"2026-07-07T16:03:10.753049Z","references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-69j4-grxj-j64p"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-62426"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/27205"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/chat_utils.py#L1602-L1610"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/blob/2a6dc67eb520ddb9c4138d8b35ed6fe6226997fb/vllm/entrypoints/openai/serving_engine.py#L809-L814"},{"type":"PACKAGE","url":"https://pypi.org/project/vllm"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-69j4-grxj-j64p"}],"affected":[{"package":{"name":"vllm","ecosystem":"PyPI","purl":"pkg:pypi/vllm"},"ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.5.5"},{"fixed":"0.11.1"}]}],"versions":["0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"],"database_specific":{"source":"https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-2012.yaml"}}],"schema_version":"1.7.5","severity":[{"type":"CVSS_V3","score":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"}]}