vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 0.32.0
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
Summary
vLLM, an open-source engine for serving large language models, is affected through its OpenAI-compatible HTTP server, which by default accepts cross-origin requests from any website. A malicious web page could use a visitor's browser to send requests to an unauthenticated vLLM server on localhost or an internal network, allowing the attacker to use the server's GPU resources and read the responses.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original description
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.
Timeline
- CVE published
- First seen by cve.now
Affected versions
- vllm-project vllm
fixed in 0.32.0
- vllmPyPI
fixed in 0.32.0