Authenticated SSRF via inconsistent backslash parsing
Published Jan 27, 2026 · Updated Jan 27, 2026
SSRF in vLLM before 0.14.1 allows remote authenticated users to make the server request arbitrary internal network resources. The MediaConnector load_from_url and load_from_url_async methods validate hostnames with urllib.parse but fetch through clients whose parsers interpret backslashes differently. Low-privileged API access to multimodal URL inputs is sufficient to bypass an allowed-domain restriction, enabling internal service discovery, sensitive-data access, or service interruption.
Summary
What happened
SSRF in vLLM before 0.14.1 allows remote authenticated users to make the server request arbitrary internal network resources. The MediaConnector load_from_url and load_from_url_async methods validate hostnames with urllib.parse but fetch through clients whose parsers interpret backslashes differently. Low-privileged API access to multimodal URL inputs is sufficient to bypass an allowed-domain restriction, enabling internal service discovery, sensitive-data access, or service interruption.
The record
- CVE
- CVE-2026-24779
- Published
- Jan 27, 2026
- Updated
- Jan 27, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-918, T1090
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jan 27, 2026CVE publishedPublication date reported by the CVE source.
- Jan 27, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.14.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
- GHSA-qh4c-xf7m-gxfc technical exploit detailsproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo