vllm-project · vLLM · published 2026-01-27
CVE-2026-24779vLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`
This month Public proof-of-concept exists (SSVC exploitation: poc).
CVE-2026-24779 has a public proof-of-concept exploit, but no confirmed exploitation in the wild. EPSS estimates a 0.6% chance of exploitation in the next 30 days, higher than 48% of all CVEs. This vLLM vulnerability: CVSS 7.1 (v3.1). Fixed upstream in vLLM 0.14.1. Patch in your normal monthly cycle.
Jump to: Remediation Exploit intelAffected versionsDescription
Remediation#
Fixed upstream in vLLM 0.14.1.
Patch events
AI toolingvLLM
vLLM security release: 0.14.1
Upgrade to
0.14.1Why: Public proof-of-concept exists (SSVC exploitation: poc).
Exploit intelligence#
| Signal | Value | Source |
|---|---|---|
| Known exploited | No | CISA KEV |
| Ransomware use | — | CISA KEV |
| EPSS (30-day exploitation probability) | 0.6% (49th pct) | FIRST EPSS v2026.06.15 |
| CVSS base score | 7.1 (v3.1)CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L | CNA / CISA ADP |
| SSVC exploitation | poc | CISA Vulnrichment |
| SSVC automatable | No | CISA Vulnrichment |
| SSVC technical impact | partial | CISA Vulnrichment |
Affected versions (from the CVE record)#
- vllm-project vllm
< 0.14.1(affected)
Description (from the CVE record)#
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.14.1, a Server-Side Request Forgery (SSRF) vulnerability exists in the `MediaConnector` class within the vLLM project's multimodal feature set. The load_from_url and load_from_url_async methods obtain and process media from URLs provided by users, using different Python parsing libraries when restricting the target host. These two parsing libraries have different interpretations of backslashes, which allows the host name restriction to be bypassed. This allows an attacker to coerce the vLLM server into making arbitrary requests to internal network resources. This vulnerability is particularly critical in containerized environments like `llm-d`, where a compromised vLLM pod could be used to scan the internal network, interact with other pods, and potentially cause denial of service or access sensitive data. For example, an attacker could make the vLLM pod send malicious requests to an internal `llm-d` management endpoint, leading to system instability by falsely reporting metrics like the KV cache state. Version 0.14.1 contains a patch for the issue.
Quoted from the CVE Program record.