What is the official website of vLLM ?

The official website of vLLM is https://github.com/vllm-project/vllm.

What is vLLM's cybersecurity risk score?

vLLM has an AI-generated cybersecurity risk score of 747 out of 1000, indicating a Moderate security posture according to Rankiteo's assessment.

How many security incidents has vLLM experienced?

According to Rankiteo, vLLM currently holds 0 security badges, indicating that no recognized compliance certifications are currently verified for the organization.

Has vLLM been affected by any supply chain cyber incidents ?

According to Rankiteo, vLLM has not been affected by any supply chain cyber incidents, and no incident IDs are currently listed for the organization.

Does vLLM have SOC 2 Type 1 certification ?

According to Rankiteo, vLLM is not certified under SOC 2 Type 1.

Does vLLM have SOC 2 Type 2 certification ?

According to Rankiteo, vLLM does not hold a SOC 2 Type 2 certification.

Does vLLM comply with GDPR ?

According to Rankiteo, vLLM is not listed as GDPR compliant.

Does vLLM have PCI DSS certification ?

According to Rankiteo, vLLM does not currently maintain PCI DSS compliance.

Does vLLM comply with HIPAA ?

According to Rankiteo, vLLM is not compliant with HIPAA regulations.

Does vLLM have ISO 27001 certification ?

According to Rankiteo,vLLM is not certified under ISO 27001, indicating the absence of a formally recognized information security management framework.

Which industry does vLLM operate in ?

vLLM operates primarily in the Software Development industry.

How many employees does vLLM have ?

vLLM employs approximately 20 people worldwide.

Does vLLM own any subsidiaries ?

vLLM presently has no subsidiaries across any sectors.

How many LinkedIn followers does vLLM have ?

vLLM's official LinkedIn profile has approximately 14,771 followers.

What is the NAICS classification code for vLLM ?

vLLM is classified under the NAICS code 5112, which corresponds to Software Publishers.

Does vLLM have a Crunchbase profile ?

No, vLLM does not have a profile on Crunchbase.

Does vLLM have a LinkedIn profile ?

Yes, vLLM maintains an official LinkedIn profile, which is actively utilized for branding and talent engagement, which can be accessed here: https://www.linkedin.com/company/vllm-project.

How many cybersecurity incidents has vLLM experienced ?

As of July 14, 2026, Rankiteo reports that vLLM has experienced 1 cybersecurity incidents.

How many peer or competitor companies does vLLM have ?

vLLM has an estimated 30,334 peer or competitor companies worldwide.

What types of cybersecurity incidents has vLLM faced ?

Incident Types: The types of cybersecurity incidents that have occurred include Vulnerability.

NEWRankiteo Cyber Underwriting Desktop - Score, price, and bind from your desktop

WindowsmacOSLinux

Download

Badge your company to reduce your risk score and your cyber insurance costs!

Link verified badges to your company page to build trust with insurers and customers.

Apply now and get your badge!

Internal validation & live display

Insurers and partners see a safer profile

Faster underwriting decisions

Trusted by insurers. Chosen by leaders.

Proud contributor to the Society of Actuaries.

vLLM

Boost Score +25 with badge (5 left)

747

/1000

Moderate

772

/1000

Fair

vLLM Vendor Cyber Rating & Cyber Score

github.com

Add Your Compliance Badge

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs

vLLM A.I CyberSecurity Scoring

Scoring History

vLLM

vLLM CyberSecurity News & History

Past Incidents

Attack Types

Entity

Type

Severity

Impact

Seen

Blog Details

Supply Chain Source

Incident Details

View

vLLM

Vulnerability

5/2026

OBOVLLFAS177989...

Loading…

A.I.

vLLM Company Scoring based on AI Models

Cyber Incidents Likelihood 3 - 6 - 9 months

Actual

Prediction

Incident Predictions locked

Access Monitoring Plan

A.I Risk Score Likelihood 3 - 6 - 9 months

Actual

Prediction A

Prediction B

Prediction C

Prediction D

A.I. Risk Score Predictions locked

Access Monitoring Plan

Loading…

Underwriter Stats for vLLM

Incidents vs Software Development Industry Avg (This Year)

vLLM has 5.66% fewer incidents than the average of same-industry companies with at least one recorded incident.

Incidents vs All-Companies Average (This Year)

vLLM has 4.76% fewer incidents than the average of all companies with at least one recorded incident.

Incident Types vLLM vs Software Development Industry Avg (This Year)

vLLM reported 1 incidents this year: 0 cyber attacks, 0 ransomware, 1 vulnerabilities, 0 data breaches, compared to industry peers with at least 1 incident.

Incident History - vLLM (X = Date, Y = Severity)

Loading…

SUBSIDIARY

vLLM Subsidiaries

Parent Company

vLLM

Software Development

Website: https://github.com/vllm-project/vllm

Company Size: 51-200 employees

No subsidiary data available for this company.

Loading…

vLLM Similar Companies

DoorDash

careersatdoordash.com

At DoorDash, our mission to empower local economies shapes how our team members move quickly and always learn and reiterate to support merchants, Dashers and the communities we serve. We are a technology and logistics company that started with door-to-door delivery, and we are looking for team members who can help us go from a company that is known for delivering food to a company that people turn to for any and all goods. DoorDash is growing rapidly and changing constantly, which gives our team members the opportunity to share their unique perspectives, solve new challenges, and own their careers. Our leaders seek the truth and welcome big, hairy, audacious questions. We are grounded in our company values, and we make intentional decisions that are both logical and display empathy for our range of users—from Dashers to Merchants to Customers.

Snowflake

snowflake.com

Snowflake delivers the AI Data Cloud — a global network where thousands of organizations mobilize data with near-unlimited scale, concurrency, and performance. Inside the AI Data Cloud, organizations unite their siloed data, easily discover and securely share governed data, and execute diverse analytic workloads. Wherever data or users live, Snowflake delivers a single and seamless experience across multiple public clouds. Snowflake’s platform is the engine that powers and provides access to the AI Data Cloud, creating a solution for data warehousing, data lakes, data engineering, data science, data application development, and data sharing. Join Snowflake customers, partners, and data providers already taking their businesses to new frontiers in the AI Data Cloud.

OpenText

cb opentext.com

OpenText is a leading Cloud and AI company that provides organizations around the world with a comprehensive suite of Business AI, Business Clouds, and Business Technology. We help organizations grow, innovate, become more efficient and effective, and do so in a trusted and secure way—through Information Management. OpenText (NASDAQ/TSX: OTEX), founded in 1991 in Waterloo, has a rich history of helping customers manage their most important asset—information. Originating from a collaboration to digitize the Oxford English Dictionary, OpenText has grown into a global leader in information management. With over 120,000 enterprise customers across 180 countries, OpenText supports 98 of the top 100 global companies. A wide breadth of offerings uniquely positions OpenText to help customers unlock the value of that information using Al, cloud, and security innovations. At OpenText, our culture is at the heart of everything we do—and today, that includes being proudly AI-first. We’re creating a workplace where everyone can thrive, with artificial intelligence integrated into how we work, solve problems, and innovate together. By fostering a collaborative and inclusive environment, we empower digital knowledge workers and drive forward-thinking solutions that shape the future of information management. We believe our success comes from the strength of our team—talent that AI can’t replace—and we’re committed to attracting and supporting those who bring unique insight, adaptability, and creativity. Because at OpenText, people aren’t just our greatest asset—they’re the reason we shine in an AI-powered world. Join us at OpenText and become part of a team where your talents and ideas are truly valued.

Bosch USA

bosch.us

The Bosch Group’s strategic objective is to create solutions for a connected life. Bosch improves quality of life worldwide with innovative products and services that are "Invented for life" and spark enthusiasm. Podcast: http://bit.ly/beyondbosch Imprint: https://www.bosch.us/corporate-information/ Privacy statement: https://bit.ly/binaprv Terms of use: We strive to provide a friendly space for all social media users. Please note that comments on the BoschUSA page are not necessarily representative of the opinions of BoschUSA, nor do we confirm their accuracy. Therefore, at its discretion, BoschUSA reserves the right to remove any comment that is: - Indecent, obscene, pornographic, threatening, violent, discriminatory, political, religious, racist, abusive, derogatory, misleading, off-topic - Violating the rights of others (especially personal, copyright and performance protection rights) - Any contribution in the form of links, text and/or images that are advertisements of third parties - Actions that adversely affect the proper functioning of BoschUSA channels, as well as documents that contain harmful viruses or Like invites.

UKG

ukg.com

UKG is the Workforce Operating Platform that puts workforce understanding to work. With the world's largest collection of workforce insights, and people-first AI, our ability to reveal unseen ways to build trust, amplify productivity, and empower talent, is unmatched. It's this expertise that equips our customers with the intelligence to solve any challenge in any industry — because great organizations know their workforce is their competitive edge.

Wolt

wolt.com

Wolt is a Helsinki-based technology company with a mission to bring joy, simplicity and earnings to the neighborhoods of the world. Wolt develops a local commerce platform that connects people looking to order food, groceries, and other goods with people interested in selling and delivering them. Wolt was founded in 2014 and joined forces with DoorDash (NASDAQ: DASH) in 2022. Together, we operate in more than 30 countries today.

Agoda

careersatagoda.com

At Agoda, we bridge the world through travel. We aim to make it easy and rewarding for more travelers to explore and experience the amazing world we live in. We do so by enabling more people to see the world for less – with our best-value deals across our 6,000,000+ hotels and holiday properties, 130,000+ flight routes, 360,000+ activities, and more. Agoda was founded in 2005 in Thailand by two lifelong friends with a shared passion for travel. Today, Agoda is part of Booking Holdings [BKNG], and we have more than 7,000 employees from 90 nationalities in offices across Asia Pacific, the Middle East, Europe, and the Americas. In every department – from engineering to customer support – you’ll find that data and technology are at the heart of our culture. There’s never a boring day at Agoda as we aim to make travel hassle-free for everyone. If you’re ready to begin your best journey with us and help us build travel for the world, join us. For properties seeking partnership with Agoda, visit https://connect.agoda.com

Workday

workday.com

Workday is a leading provider of enterprise cloud applications for finance and human resources, helping customers adapt and thrive in a changing world. Workday applications for financial management, human resources, planning, spend management, and analytics are built with artificial intelligence and machine learning at the core to help organizations around the world embrace the future of work. Workday is used by more than 10,000 organizations around the world and across industries – from medium-sized businesses to more than 50% of the Fortune 500.

Red Hat

redhat.com

Red Hat is the world’s leading provider of enterprise open source solutions, using a community-powered approach to deliver high-performing Linux, hybrid cloud, edge, and Kubernetes technologies. We hire creative, passionate people who are ready to contribute their ideas, help solve complex problems, and make an impact. Opportunities are open. Join us.

Loading…

NEWS

vLLM CyberSecurity News

Latest updates, reports, and threat intel affecting the global network.

December 17, 2025 11:09 PM

Zeroday Cloud hacking event awards $320,0000 for 11 zero days

The Zeroday Cloud hacking competition in London has awarded researchers $320,000 for demonstrating critical remote code execution...

Read Article

November 24, 2025 08:00 AM

vLLM Vulnerability Enables Remote Code Execution Via Malicious Payloads

A memory bug in vLLM versions 0.10.2 and later lets attackers run remote code by sending harmful prompt embeddings to the Completions API.

Read Article

November 24, 2025 08:00 AM

vLLM Flaw Allows Remote Code Execution Through Malicious Payloads

A high security vulnerability has been discovered in vLLM, a widely used high-throughput inference and serving engine for Large Language...

Read Article

November 17, 2025 08:00 AM

Critical RCE Flaws in AI Inference Engines Expose Meta, Nvidia, and Microsoft Frameworks

Security researchers at Oligo Security have uncovered a series of critical Remote Code Execution vulnerabilities affecting widely deployed...

Read Article

November 17, 2025 08:00 AM

Critical RCE Vulnerabilities in AI Inference Engines Exposes Meta, Nvidia and Microsoft Frameworks

As artificial intelligence infrastructure rapidly expands, critical security flaws threaten the backbone of enterprise AI deployments.

Read Article

November 14, 2025 08:00 AM

Researchers Find Serious AI Bugs Exposing Meta, Nvidia, and Microsoft Inference Frameworks

Cybersecurity researchers have uncovered critical remote code execution vulnerabilities impacting major artificial intelligence (AI)...

Read Article

November 14, 2025 08:00 AM

Copy-paste vulnerability hits AI inference frameworks at Meta, Nvidia, and Microsoft

Flaws replicated from Meta's Llama Stack to Nvidia TensorRT-LLM, vLLM, SGLang, and others, exposing enterprise AI stacks to systemic risk.

Read Article

October 15, 2025 07:00 AM

Red Hat AI 3 Puts Inference Front and Center

Red Hat AI 3 unifies OpenShift, Linux, and AI Inference Server to help enterprises scale, manage, and optimize AI workloads across...

Read Article

May 27, 2025 07:00 AM

Red Hat and AMD Team Up to Boost AI Processing Power and Performance

Red Hat and AMD have announced a significant strategic collaboration aimed at enhancing processing power and performance for artificial intelligence workloads.

Read Article

Loading…

CVE

Latest

Global CVEs (Not Company-Specific)

CVE-2026-58489

SUMMARY

HedgeDoc is an open source, real-time collaborative markdown notes application. Prior to 1.11.0, the GitHub Gist export flow created an OAuth2 state value but only checked that it was present rather than validating it against the value expected for the user's session. Because the state was not properly validated, an attacker could forge a callback URL containing their own valid GitHub OAuth code. When processing the callback, HedgeDoc used the victim's logged-in session to select which note to export, but the attacker's authorization code to determine which GitHub account received it. As a result, a logged-in victim who clicked a crafted link could export their own private, protected, or limited note directly into a Gist controlled by the attacker. This issue has been fixed in version 1.11.0.

Published

Date2026-07-13

Updated

Date2026-07-13

RISK INFORMATION (Score: )

cvss4

Base Score: 6.8

Complexity: HIGH

CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:A/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Impact Score

Exploitability

REFERENCES

CVE-2026-58486

SUMMARY

HedgeDoc is an open source, real-time, collaborative, markdown notes application. Prior to version 1.11.0, HedgeDoc was vulnerable to a YAML alias bomb due to unsafe processing of the note frontmatter. HedgeDoc parsed frontmatter with js-yaml.load (js-yaml v3) via @hedgedoc/meta-marked, which resolved YAML anchor aliases. A compact malicious payload could therefore expand into a huge object structure, consuming excessive CPU. This expansion ran on every request to the publish view (/s/<shortid>) and, when placed under the opengraph key, the editor view (/<noteId>). A ten-level alias bomb could block the single Node.js event loop for roughly 235 seconds per request, causing concurrent requests to hang or drop and rendering the instance unavailable (DoS). Because the note was stored in the database, the impact survived process restarts until the note was removed. toobusy-js did not reliably mitigate the worst cases, as the event loop was saturated before the middleware could respond. This issue was fixed in version 1.11.0.

Published

Date2026-07-13

Updated

Date2026-07-13

RISK INFORMATION (Score: )

cvss4

Base Score: 8.3

Complexity: LOW

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Impact Score

Exploitability

REFERENCES

CVE-2026-58102

SUMMARY

Crypt::OpenSSL::X509 versions before 2.1.3 for Perl allow a heap out-of-bounds read via a long certificate extension OID in hv_exts. When building the extension hash (via extensions(), extensions_by_long_name(), extensions_by_oid(), or has_extension_oid()), the code passes OBJ_obj2txt()'s return value as the hash-key length; because that value is the OID's full text length rather than the bytes written to the fixed-size buffer (129 bytes), an OID whose text is longer than the 129-byte buffer causes a read past the allocation, exposing adjacent heap memory as the returned hash key. extensions_by_name() uses the static shortname path and is not affected.

Published

Date2026-07-13

Updated

Date2026-07-13

RISK INFORMATION (Score: )

Impact Score

Exploitability

REFERENCES

CVE-2026-58101

SUMMARY

Crypt::OpenSSL::X509 versions before 2.1.3 for Perl allow denial of service via NULL pointer dereference. X509V3_EXT_d2i(ext) returns NULL when an extension's DER value fails to parse. basicC, ia5string, and auth_att dereference its result without a NULL check. keyid_data also dereferences akid->keyid, which is NULL for an empty AKI SEQUENCE (DER 30 00) even when the parse succeeds. A caller invoking an affected helper on an extension from an untrusted certificate triggers a SIGSEGV that crashes the Perl process.

Published

Date2026-07-13

Updated

Date2026-07-13

RISK INFORMATION (Score: )

Impact Score

Exploitability

REFERENCES

CVE-2026-57856

SUMMARY

Cockpit CMS contains a path traversal vulnerability in the Bucket file storage API (/system/buckets/api). The api() method in modules/System/Controller/Buckets.php sanitizes the bucket name with preg_replace('/[^a-zA-Z0-9-_\\.]/','', $bucket), which permits '..' and '../' sequences. The sanitized value is interpolated into a Flysystem path as uploads://buckets/{bucket}. Flysystem's WhitespacePathNormalizer resolves 'buckets/..' to the empty string (the uploads storage root) without raising PathTraversalDetected because the '..' has a preceding component to consume. An authenticated low-privileged user can send a crafted request with a '../' bucket name to list, upload, and delete files across all buckets, including those belonging to other users or roles

Published

Date2026-07-13

Updated

Date2026-07-13

RISK INFORMATION (Score: 8.8)

cvss3

Base Score: 8.8

Complexity: LOW

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

cvss4

Base Score: 8.7

Complexity: LOW

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Impact Score

5.9

Exploitability

2.8

REFERENCES

Loading…

API

Access Data Using Our API

Get company history

curl -i -X GET 'https://api.rankiteo.com/underwriter-getcompany-history?
linkedin_id=axa' -H 'apikey: YOUR_API_KEY_HERE'

Try It API Documentation Rapid

MEASURE

What Do We Measure ?

Incident

Finding

Grade

Digital Assets

Every week, Rankiteo analyzes billions of signals to give organizations a sharper, faster view of emerging risks. With deeper, more actionable intelligence at their fingertips, security teams can outpace threat actors, respond instantly to Zero-Day attacks, and dramatically shrink their risk exposure window.

These are some of the factors we use to calculate the overall score:

Network SecurityIdentify exposed access points, detect misconfigured SSL certificates, and uncover vulnerabilities across the network infrastructure.

SBOM (Software Bill of Materials)Gain visibility into the software components used within an organization to detect vulnerabilities, manage risk, and ensure supply chain security.

CMDB (Configuration Management Database)Monitor and manage all IT assets and their configurations to ensure accurate, real-time visibility across the company's technology environment.

Threat IntelligenceLeverage real-time insights on active threats, malware campaigns, and emerging vulnerabilities to proactively defend against evolving cyberattacks.

Rankiteo

By Rankiteo

★ ★ ★ ★ ★

View on G2.com

Rankiteo is a unified scoring and risk platform that analyzes billions of signals weekly to help organizations gain faster, more actionable insights into emerging threats. Empowering teams to outpace adversaries and reduce exposure.

View latest plans →View all security reports →

MILESTONEG

Users
Love Us

Loading…