CVE•Published 2026-06-22•Modified 2026-09-01•1 article on news•6 live references•NVD data
CVE-2026-48746Vllm · Vllm
Vulnerability data via NVD (ingested)
CVSS v3.1
9.1
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
EPSS percentile
64
Exploit Prediction Scoring System · top 36% of all CVEs
Weaknesses (CWE)
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in ASGI web servers and starlette's trust on those web servers enables an authentication bypass of the OpenAI API AuthenticationMiddleware. It allows to use the API without providing the configured VLLM_API_KEY or --api-key. This vulnerability is fixed in 0.22.0.
Timeline
Published 2026-06-22
Modified 2026-09-01
External references
Search for exposed instances
Shodan + Censys queries derived from NVD's CPE data. The vuln tag catches assets Shodan has explicitly linked to this CVE; the product / banner fingerprints find exposed instances even when the vuln tag was never applied (which is common).
Shodan · vuln tag0 hosts
vuln:CVE-2026-48746Hosts Shodan has explicitly fingerprinted as vulnerable.
Shodan · product
product:"Vllm Vllm"All exposed Vllm Vllm instances — cross-reference with the CVE's affected-version range.
Shodan · banner/body mention
http.html:"Vllm"HTTP body or banner mentions "Vllm" — catches deploys Shodan didn't identify as a product.
More intel sources (5)
Shodan report
vuln:CVE-2026-48746Country / ASN / product breakdown for the vuln query.
Censys
vulnerabilities.cve_id: CVE-2026-48746Censys host search filtered to this CVE id.
grep.app
CVE-2026-48746Public source-code mentions — fast PoC discovery.
GitHub code
CVE-2026-48746GitHub code search for direct mentions.
Google dork
"CVE-2026-48746" exploit -site:nvd.nist.govWrite-ups and news, NVD excluded.
Known PoCs on GitHub (3)
CVE-2026-487463 repos
webpro255/awesome-ai-agent-attacksunknown
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
rmacy/qwen36-b70-mtp2Python
Reproducible Qwen3.6-27B FP8 MTP2 runtime and benchmark kit for dual Intel BMG GPUs
rmacy/glimmer-b70-vllmPython
Native Muse Glimmer 30B runtime for two Intel Arc Pro B70 GPUs