Skip to main content
cvebuzz

CVE mentions, exploit signals, and PoC evidence in one fast public view.

CVE detail

CVE-2026-73559

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.

CVSS 6.5 · MediumBuzz score 21.1

Buzz score

Why this CVE is surfacing

Buzz score total 21.1

This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.

Buzz score components · mention 16.1 · diversity 5.0 · KEV 0.0 · OTX 0.0 · PoC 0.0
Mention score
16.1
4 evidence mentions in the snapshot
Diversity score
5.0
1 sources across 1 categories
KEV score
0.0
No KEV entry observed
OTX score
0.0
0 OTX pulses
PoC score
0.0
0 repos · best confidence N/A
Best PoC traction
0
Maximum stars on a matched PoC repo

Why it matters now

Mention timeline

Total mentions
4
within the 30d window
Peak daily
4
highest bucket

Evidence

Source links by recency

Newest mentions first
4 source links · newest first

Exploit code

Public exploit repository references

Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.

0 repository references · best confidence N/A · max 0 stars
No public PoC repositories have been matched yet.

Related records

Similar CVEs

6 related CVEs with shared weakness or product evidence
  • CVE-2026-74797

    OpenTofu versions before 1.11.4 contain a denial of service vulnerability in the tofu init command when processing maliciously-crafted .zip archives for provider or module package…

    CVSS 2.3 · Low
    2 mentions
  • CVE-2026-74789

    Scriban before 7.0.0 (affected <= 6.6.0) applies its LoopLimit constraint only to script loop statements and not to expensive iteration performed inside built-in operators and fun…

    CVSS 8.7 · High
    2 mentions
  • CVE-2026-74785

    Scriban before 7.0.0 contains three distinct denial-of-service vulnerabilities in expression evaluation that bypass existing safety controls through unbounded string multiplicatio…

    CVSS 7.1 · High
    2 mentions
  • CVE-2026-73057

    stoatchat before 0.15.0 fails to validate SVG viewBox dimensions in the proxy endpoint, allowing attackers to cause denial of service by memory exhaustion. Attackers can host mali…

    CVSS 8.7 · High
    2 mentions
  • CVE-2026-18549

    @fastify/multipart is a multipart form-data parser for Fastify. In versions from 5.3.0 up to but not including 10.1.1, when the busboy fileSize limit truncates a file part, the pl…

    CVSS 7.5 · High
    2 mentions
  • CVE-2026-73634

    Uncontrolled resource consumption vulnerability in Apache Struts. An application that exposes an endpoint collecting Content Security Policy violation reports reads the submitted…

    CVSS N/A · Unrated
    1 mention