CVE-2026-24779
CVE-2026-24779 is a high-severity vulnerability in Vllm with a CVSS 3.x base score of 7.1. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-918.
Key facts
- Severity: High (CVSS 3.x base score 7.1)
- EPSS exploit prediction: 1% (41st percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2026-4711
- Weakness: CWE-918
- Affected product: Vllm
- Published:
- Last modified:
Description
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.
Frequently asked questions
- What is CVE-2026-24779?
- 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.
- How severe is CVE-2026-24779?
- CVE-2026-24779 has a CVSS 3.x base score of 7.1, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability low.
- Is CVE-2026-24779 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (41st percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2026-24779?
- CVE-2026-24779 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2026-24779?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2026-24779 have an EU (EUVD) identifier?
- Yes. CVE-2026-24779 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-4711.
- When was CVE-2026-24779 published?
- CVE-2026-24779 was published on 2026-01-27 and last updated on 2026-06-30.
References
- https://github.com/vllm-project/vllm/commit/f46d576c54fb8aeec5fc70560e850bed38ef17d7
- https://github.com/vllm-project/vllm/pull/32746
- https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
- https://access.redhat.com/errata/RHSA-2026:10184
- https://access.redhat.com/errata/RHSA-2026:19712
- https://access.redhat.com/errata/RHSA-2026:30087
- https://access.redhat.com/errata/RHSA-2026:30088
- https://access.redhat.com/errata/RHSA-2026:30089
- https://access.redhat.com/errata/RHSA-2026:3461
- https://access.redhat.com/errata/RHSA-2026:3462
- https://access.redhat.com/errata/RHSA-2026:3782
- https://access.redhat.com/security/cve/CVE-2026-24779
- https://bugzilla.redhat.com/show_bug.cgi?id=2433624
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-24779.json
Affected products (1)
- cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
More vulnerabilities in Vllm
- CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
- CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
- CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
- CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
- CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
- CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…
Other CWE-918 (Server-Side Request Forgery (SSRF)) vulnerabilities
- CVE-2026-47938 — Critical (CVSS 10.0): Adobe Campaign Classic (ACC) versions 7.4.3 build 9394 and earlier are affected by a Server-Side Request Forgery (SSRF)…
- CVE-2026-35431 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Microsoft Entra ID Entitlement Management allows an unauthorized attacker to…
- CVE-2026-32186 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Microsoft Bing allows an unauthorized attacker to elevate privileges over a…
- CVE-2026-33107 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Azure Databricks allows an unauthorized attacker to elevate privileges over a…
- CVE-2026-32871 — Critical (CVSS 10.0): FastMCP is a Pythonic way to build MCP servers and clients. Prior to version 3.2.0, the OpenAPIProvider in FastMCP…
- CVE-2026-32169 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Azure Cloud Shell allows an unauthorized attacker to elevate privileges over a…
Browse all CWE-918 (Server-Side Request Forgery (SSRF)) vulnerabilities →