CVE•Published 2026-03-27•Modified 2026-07-21•1 article on news•5 live references•NVD data
CVE-2026-27893Vllm · Vllm
Vulnerability data via NVD (ingested)
CVSS v3.1
8.8
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS percentile
69
Exploit Prediction Scoring System · top 31% of all CVEs
Description
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.
Timeline
Published 2026-03-27
Modified 2026-07-21
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-2026-27893Hosts 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-2026-27893Country / ASN / product breakdown for the vuln query.
Censys
vulnerabilities.cve_id: CVE-2026-27893Censys host search filtered to this CVE id.
grep.app
CVE-2026-27893Public source-code mentions — fast PoC discovery.
GitHub code
CVE-2026-27893GitHub code search for direct mentions.
Google dork
"CVE-2026-27893" exploit -site:nvd.nist.govWrite-ups and news, NVD excluded.