Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-73559— vLLM: Completion prompt lists fan out into unbounded engine requests

Quick assessment

Affected
vllm-project vllm
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM 是用于大型语言模型的推理和服务引擎。从版本 0.19.0 到 0.26.0，vllm/entrypoints/openai/completion/protocol.py 中的 /v1/completions CompletionRequest.prompt 字段接受无限制的 list[str] 或 list[list[int]]。vllm/renderers/inputs/preprocess.py 中的 prompt_to_seq() 以及 vllm/renderers/online_renderer.

CVSS 6.5 · Medium EPSS 0.58% · P46

Possible ATT&CK Techniques 1 AI

T1499 · Endpoint Denial of Service

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm >= 0.19.0, < 0.26.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-73559

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM: Completion prompt lists fan out into unbounded engine requests
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.preprocess_completion() in vllm/renderers/online_renderer.py expand every element, and vllm/entrypoints/openai/completion/serving.py creates one engine generator and response slot per prompt, allowing an authenticated API client to exhaust CPU, memory, async scheduling capacity, engine request slots, and response buffering with one request. This issue is fixed in version 0.26.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
未加控制的资源消耗(资源穷尽)
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vllm >= 0.19.0, < 0.26.0 -

II. Public POCs for CVE-2026-73559

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-73559

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-73559 (2)

Vendor Advisories for CVE-2026-73559 (1)

Vendor Pages for CVE-2026-73559 (1)

Same Patch Batch · vllm-project · 2026-08-13 · 5 CVEs total

CVE-2026-73557 6.3 MEDIUM vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
CVE-2026-73555 5.3 MEDIUM vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages
CVE-2026-73556 5.3 MEDIUM vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile tim
CVE-2026-73558 5.3 MEDIUM vLLM: Cross-User Data Leak Vulnerability

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-400

V. Comments for CVE-2026-73559

No comments yet

Leave a comment