Function reliability_guard

metrics/code_eval/execute.py:158–236

This disables various destructive functions and prevents the generated code from interfering with the test (e.g. fork bomb, killing other processes, removing filesystem files, etc.) WARNING This function is NOT a security sandbox. Untrusted code, including, model- generated

(maximum_memory_bytes=None)

def reliability_guard(maximum_memory_bytes=None):
    """
    This disables various destructive functions and prevents the generated code
    from interfering with the test (e.g. fork bomb, killing other processes,
    removing filesystem files, etc.)

    WARNING
    This function is NOT a security sandbox. Untrusted code, including, model-
    generated code, should not be blindly executed outside of one. See the
    Codex paper for more information about OpenAI's code sandbox, and proceed
    with caution.
    """

    if maximum_memory_bytes is not None:
        import resource

        resource.setrlimit(resource.RLIMIT_AS, (maximum_memory_bytes, maximum_memory_bytes))
        resource.setrlimit(resource.RLIMIT_DATA, (maximum_memory_bytes, maximum_memory_bytes))
        if not platform.uname().system == "Darwin":
            resource.setrlimit(resource.RLIMIT_STACK, (maximum_memory_bytes, maximum_memory_bytes))

    faulthandler.disable()

    import builtins

    builtins.exit = None
    builtins.quit = None

    import os

    os.environ["OMP_NUM_THREADS"] = "1"

    os.kill = None
    os.system = None
    os.putenv = None
    os.remove = None
    os.removedirs = None
    os.rmdir = None
    os.fchdir = None
    os.setuid = None
    os.fork = None
    os.forkpty = None
    os.killpg = None
    os.rename = None
    os.renames = None
    os.truncate = None
    os.replace = None
    os.unlink = None
    os.fchmod = None
    os.fchown = None
    os.chmod = None
    os.chown = None
    os.chroot = None
    os.fchdir = None
    os.lchflags = None
    os.lchmod = None
    os.lchown = None
    os.getcwd = None