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.

There are packages installed that are affected by a vulnerability referenced in the following CVE:

  - 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. (CVE-2026-24779)

ID	Name	Product	Family	Type	Severity
437353	SCA: security update for vllm (GHSA-qh4c-xf7m-gxfc)	Tenable Cloud Security	SCA Checks	Local	high
437353	SCA: security update for vllm (GHSA-qh4c-xf7m-gxfc)	Tenable Self-Hosted Container Security	SCA Checks	Local	high

Detections

Analytics

CVE-2026-24779

high

Tenable Plugins

high

high