CVE-2026-24779

Medium

Elevated severity or exploit probability.

CVSS base

7.1 HIGH

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

EPSS — probability of exploitation (30 days)

0.6%

45.8th percentile

CISA KEV

Not listed

Weakness / dates

CWE-918

Published 2026-01-27 · modified 2026-07-21

CVSS breakdown

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

Attack Vector	N	Network
Attack Complexity	L	Low
Privileges Required	L	Low
User Interaction	N	None
Scope	U	Unchanged
Confidentiality	H	High
Integrity	N	None
Availability	L	Low

Timeline

2026-01-27 — Published (NVD)
2026-07-21 — Last modified (NVD)

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.

Affected

vllm

References

Official: NVD · CVE.org