PYSEC-2026-4349
See a problem?- Import Source
- https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4349.yaml
- JSON Data
- https://api.osv.dev/v1/vulns/PYSEC-2026-4349
- Aliases
- Published
- 2026-10-26T18:17:39Z
- Modified
- 2026-10-29T11:00:02Z
- Severity
-
- 6.5 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
- Summary
- [none]
- Details
-
vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.
- References
Affected packages
PyPI / vllm
Package
- Name
- vllm
- View open source insights on deps.dev
- Purl
- pkg:pypi/vllm