Details
The user is not warned that arbitrary Python from the repo will
execute, and there is no flag to disable it. The CVE class is
CWE-94 (Improper Control of Generation of Code, supply-chain
flavour) and CWE-915 (Improperly Controlled Modification of
Dynamically-Determined Object Attributes).
Comparison to peer projects
| Project | trust_remote_code default | User control |
|---|---|---|
| HuggingFace Transformers | False | trust_remote_code keyword arg |
| vLLM | False | --trust-remote-code flag |
| LMDeploy | True (hardcoded) | None |
| TGI | False | --trust-remote-code flag |
LMDeploy is the outlier. The rationale is presumably "internal
models like InternLM need custom configuration_*.py", but the fix is
to accept a CLI flag like --trust-remote-code and default-False as
the rest of the ecosystem does.
Suggested fix
Replace every hardcoded trust_remote_code=True with an explicit
opt-in via CLI flag:
# lmdeploy/archs.py — get_model_arch
def get_model_arch(model_path: str, trust_remote_code: bool = False):
try:
cfg = AutoConfig.from_pretrained(model_path, trust_remote_code=trust_remote_code)
except Exception as e: # noqa
from transformers import PretrainedConfig
cfg = PretrainedConfig.from_pretrained(model_path, trust_remote_code=trust_remote_code)
Wire trust_remote_code through every call site. Add --trust-remote-code
to lmdeploy's CLI parser and forward it from server / calibrate /
gptq / etc. Default False.
A patch fragment is in patch.diff.
Disclosure plan
- Submit privately via lmdeploy security contact (typically email or GitHub Security Advisory at
https://github.com/InternLM/lmdeploy/security/advisories/new). - Reference Hugging Face Transformers' historical opt-out → opt-in change as precedent for the fix shape.
- 90-day coordinated-disclosure window starting from acknowledgement.
- Request CVE through GHSA flow once the patch lands.
Why static-only is sufficient here
Unlike F11 (RCE chain through _load_pt_file) which required a
runtime PoC to demonstrate the pickle gadget execution, this finding
is a single trust-flag flip — the behaviour ofAutoConfig.from_pretrained(repo, trust_remote_code=True) on a HF
repo with a malicious configuration_*.py is documented behaviour of
HF Transformers itself (their own docs warn against it). Reproducing
it adds no new evidence; the static flag-state is the bug.
If the vendor requests a runtime PoC during triage we will provide
one (a malicious HF repo with configuration_evil.py + a one-linerlmdeploy lite calibrate <repo> invocation), but holding it back from
the initial advisory avoids publishing a working exploit during the
disclosure window.