Summary lmdeploy hardcodes trust_remote_code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: ``text lmdeploy/archs.py lmdeploy/utils.py `` The vulnerable call sites pass trust_remo…
| CVE ID | CVE-2026-46432 |
| Vendor | pip |
| Affected Product | lmdeploy |
| Vulnerability Type | Vulnerability |
| CVSS Score | 7.8 (HIGH) |
| Actively Exploited | ❌ No known exploitation |
| Patch Status | See Vendor Advisory → |
| Reported By | CYBERDUDEBIVASH SENTINEL APEX Intelligence (via github_advisories) |
#
trust_remote_code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: ``textlmdeploy/archs.py lmdeploy/utils.py `` The vulnerable call sites pass trust_remote_code=True into HuggingFace Transformers APIs such as AutoConfig.from_pretrained(), PretrainedConfig.get_config_dict(), and GenerationConfig.from_pretrained(). Because the model path is supplied by the operator or deployment configuration, an attacker who can control the model_path` used by an lmdeploy serving process can point it to an attacker-controlled HuggingFace model repository. When lmdeploy starts and initializes the model, Transformers may download and execute remote Python code from that repository. Successful exploitation results in arbitrary c
Sigma rules, YARA signatures, IOC table, and SIEM queries for Splunk, Elastic, Sentinel, and Chronicle — deployable in 5 minutes.