Medium

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

  • Disclosed: 26.10.2026
  • Updated: 29.10.2026 13:17

Summary

vLLM's /v1/responses endpoint accepts request-level chat_template_kwargs, but does not apply the --trust-request-chat-template gate that protects Chat Completions, render, tokenize, and pooling paths.

When the server is run with the documented default trust_request_chat_template=False and no explicit --chat-template, a Responses request can pass:

js
{"chat_template_kwargs": {"chat_template": "<attacker Jinja template>"}}

That key is preserved by ChatParams.get_apply_chat_template_kwargs() and then bound as the chat_template parameter to the shared HF renderer. Prior vLLM advisories establish that request-controlled Jinja chat templates can cause CPU/memory exhaustion. This report covers the current-head Responses sibling path missed by the earlier fixes.

Technical Details

The shared OpenAI frontend has a validation helper that rejects request-supplied chat templates unless the trust flag is enabled. It explicitly checks both top-level chat_template and chat_template_kwargs["chat_template"].

Responses is a separate serving path:

  • vllm/entrypoints/openai/responses/protocol.py exposes chat_template_kwargs.
  • ResponsesRequest.build_chat_params() merges request kwargs.
  • OpenAIServingResponses._effective_chat_template_kwargs() uses those kwargs.
  • ChatParams.get_apply_chat_template_kwargs() preserves a request chat_template key when the server chat template is None.
  • vllm/renderers/hf.py unpacks the result into safe_apply_chat_template.

There is no equivalent trust gate in vllm/entrypoints/openai/responses/serving.py.

Impact

An authenticated caller who can submit /v1/responses requests can supply a request-controlled Jinja chat template despite the trust flag being disabled. The expected fixed behavior is the same as Chat Completions: reject chat_template_kwargs["chat_template"] unless the server was started with --trust-request-chat-template.

Suggested Fix

  • Add trust_request_chat_template to OpenAIServingResponses.
  • Pass args.trust_request_chat_template when constructing the Responses serving object.
  • Reject request.chat_template_kwargs["chat_template"] before rendering when trust is false.
  • Keep ordinary kwargs such as enable_thinking working.
  • Add regression tests for default-deny and opt-in-allow behavior on /v1/responses.

Affected Package/Versions

Source sweep found the affected shape in:

  • v0.16.0
  • v0.18.0
  • v0.20.0
  • v0.21.0
  • v0.22.0
  • v0.22.1
  • v0.23.0
  • current checkout 470229c37efaf69c86e8bc97482b0b1ff7551c65
  • current origin/main b3f0a0a0df76dda92ec4b2c9335f77e84adad911

Suggested affected range:

>= 0.16.0, <= 0.23.0

Appendix: Duplicate Research

This is related to, but distinct from:

  • GHSA-6fvq-23cw-5628 / CVE-2025-61620
  • GHSA-69j4-grxj-j64p / CVE-2025-62426

Those advisories establish the security impact of request-controlled Jinja templates and chat_template_kwargs, but they cover older Chat Completions/tokenize implementations. This report covers a current /v1/responses sibling path that still lacks the trust gate.

Local prior submissions this report..029 do not cover this root cause.

This advisory was fixed in MR50300.

Affected software

Click a technology to see all vulnerabilities affecting it.

PlatformPackageVulnerable versionsFixed in
Python (PyPI) vllm >= 0.16.0, < 0.32.0 0.32.0

References

CVSS score 6.5/10
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weakness (CWE)
CWE-400, CWE-770
Platform
Python (PyPI)
Package
vllm
Disclosed
26.10.2026
Updated
29.10.2026 13:17

Sources and licenses

OSV / GitHub Advisory Database - PYSEC-2026-4349 - PyPA Advisory Database; CC BY 4.0

OSV / GitHub Advisory Database - GHSA-x567-49g5-p4cf - CC BY 4.0

Vulnerability history: vllm

All published vulnerabilities of this package (Python (PyPI)), newest first. Shows whether this is a one-off slip or a package that needs watching.

All (107) in the archive
Total entries
107
First → latest
09.2024 10.2026
Without a fix
5
Exploited in attacks
0

Severity breakdown

  • Critical 10
  • High 25
  • Medium 55
  • Low 4
  • Unrated 13

Disclosures per year

  1. 2024: 2
  2. 2025: 30
  3. 2026: 75
Severity:
  1. vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs this entry
    Medium · 6.5 CVE-2026-115918 >= 0.16.0, < 0.32.0 0.32.0
  2. Critical · 9.8 CVE-2026-115915 >= 0.30.0, < 0.32.0 0.32.0
  3. High · 7.5 CVE-2026-54234 >= 0.17.1, < 0.24.0 0.24.0
  4. High CVE-2026-55514 >= 0.12.0, < 0.24.0 0.24.0
  5. Critical · 9.1 CVE-2026-48746 >= 0.3.0, < 0.22.0 0.22.0
  6. Critical · 9.8 CVE-2026-22778 >= 0.8.3, < 0.14.1 0.14.1
  7. High · 8.8 CVE-2026-22807 >= 0.10.1, < 0.14.0 0.14.0
  8. High · 8.8 CVE-2026-56340 >= 0.10.2, < 0.13.0 0.13.0
  9. High · 6.5 CVE-2025-62372 >= 0.5.5, < 0.11.1 0.11.1
Show more (16) Showing 20 of 36

Know which vulnerabilities affect your application

With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.

Connect your application
DockRay newsletter

Application security in your inbox

Important vulnerabilities, actionable guidance and practical advice for your applications. Choose your technologies and follow what matters to your project.

  • A daily digest of new vulnerabilities, critical ones included.
  • Notifications about important updates.
  • Practical advice on application security and monitoring.

Leave empty to receive updates for every technology.

Free to subscribe. Unsubscribe with one click in any email.