CVE-2026-24779: vLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`

Vulnerability summary

CVE-2026-24779 is a high (CVSS 7.1) Server-Side Request Forgery (SSRF) vulnerability in vllm-project vllm. EPSS estimates a 0.59% chance of exploitation in the next 30 days, higher than 47.3% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 27-01-2026
   PublishedVulnerability first disclosed.
2. 21-07-2026
   Last modifiedVulnerability information updated.

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.

• CWE-918Server-Side Request Forgery (SSRF)The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.