SB2025121147 - Multiple vulnerabilities in vLLM

Description

This security bulletin contains information about 3 secuirty vulnerabilities.

1) Covert timing channel (CVE-ID: CVE-2025-59425)

The vulnerability allows a remote attacker to perform a brute-force attack.

The vulnerability exists within the API key validation process, which uses a string comparison that takes longer the more characters the provided API key gets correct. A remote attacker can perform a timing attack and brute-force the API key. 

2) Server-Side Request Forgery (SSRF) (CVE-ID: CVE-2025-6242)

The disclosed vulnerability allows a user attacker to perform SSRF attacks.

The vulnerability exists due to insufficient validation of user-supplied input within the load_from_url() and load_from_url_async() functions of MediaConnector class. A remote user can send a specially crafted HTTP request and trick the application to initiate requests to arbitrary systems.

Successful exploitation of this vulnerability may allow a remote attacker gain access to sensitive data, located in the local network or send malicious requests to other servers from the vulnerable system.

3) Resource exhaustion (CVE-ID: CVE-2025-61620)

The vulnerability allows a remote user to perform a denial of service (DoS) attack.

The vulnerability exists due to application does not properly control consumption of internal resources in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chat_template and chat_template_kwargs parameters. A remote user can trigger resource exhaustion and perform a denial of service (DoS) attack.

Remediation

Install update from vendor's website.

References

• https://github.com/vllm-project/vllm/blob/4b946d693e0af15740e9ca9c0e059d5f333b1083/vllm/entrypoints/openai/api_server.py#L1270-L1274
• https://github.com/vllm-project/vllm/commit/ee10d7e6ff5875386c7f136ce8b5f525c8fcef48
• https://github.com/vllm-project/vllm/releases/tag/v0.11.0
• https://github.com/vllm-project/vllm/security/advisories/GHSA-wr9h-g72x-mwhm
• https://github.com/vllm-project/vllm/security/advisories/GHSA-3f6c-7fw2-ppm4
• https://github.com/vllm-project/vllm/security/advisories/GHSA-6fvq-23cw-5628