Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| vllm-project | vllm-project/vllm | affected |
|
No data.
No data.
| Vendor | Product | Versions | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Vllm-project | Vllm |
|
No CVSS v4.0
No CVSS v3.1
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.747% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| Description | vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted. | |
| Title | Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control | |
| Weaknesses | CWE-22 | |
| References |
| |
| Metrics |
cvssV3_0
|