vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

Summary

An assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1).

Details

vLLM uses an assert statement at vllm/model_executor/layers/pooler/activations.py:48 as its sole security control to restrict which activation functions can be loaded from a HuggingFace model's config.json:

# vllm/model_executor/layers/pooler/activations.py:35-53
function_name: str | None = None
if (
    hasattr(config, "sentence_transformers")
    and "activation_fn" in config.sentence_transformers
):
    function_name = config.sentence_transformers["activation_fn"]
elif (
    hasattr(config, "sbert_ce_default_activation_function")
    and config.sbert_ce_default_activation_function is not None
):
    function_name = config.sbert_ce_default_activation_function

if function_name is not None:
    assert function_name.startswith("torch.nn.modules."), (
        "Loading of activation functions is restricted to "
        "torch.nn.modules for security reasons"
    )
    fn = resolve_obj_by_qualname(function_name)()

Python's assert statements are stripped at compile time when running in optimized mode (python -O or PYTHONOPTIMIZE=1). When the assert is absent, the attacker-controlled function_name from the model's config.json is passed directly to resolve_obj_by_qualname() — an unrestricted import gadget:

def resolve_obj_by_qualname(qualname: str) -> Any:
    module_name, obj_name = qualname.rsplit(".", 1)
    module = importlib.import_module(module_name)
    return getattr(module, obj_name)

This is the same vulnerability class as CVE-2017-1000433 (pysaml2 assert-based auth bypass), flagged by Bandit B101 and Ruff S101, and the reason Django proactively replaced all assert-based security checks (ticket #32508).

Attacker-controlled input sources:

• config.sentence_transformers["activation_fn"] (line 40)
• config.sbert_ce_default_activation_function (line 45)

Affected call sites — get_act_fn() is called via resolve_classifier_act_fn() from:

• vllm/model_executor/layers/pooler/seqwise/poolers.py:122 — SequencePooler
• vllm/model_executor/layers/pooler/tokwise/poolers.py:130 — TokenPooler

Broader systemic risk: resolve_obj_by_qualname is called from ~20 locations across the codebase with no validation of its own. Any future caller feeding user-controlled input to it without validation creates the same vulnerability class.

Suggested fix: Replace the assert with an explicit conditional raise:

if not function_name.startswith("torch.nn.modules."):
    raise ValueError(
        "Loading of activation functions is restricted to "
        "torch.nn.modules for security reasons"
    )

Impact

Arbitrary code execution. A malicious model author publishes a HuggingFace model with a crafted config.json. When a victim loads this model with vLLM running under python -O or PYTHONOPTIMIZE=1, arbitrary code executes during model initialization with the privileges of the vLLM process.

The attack requires:

1. Victim loads a malicious model from HuggingFace (user interaction)
2. vLLM runs under python -O or PYTHONOPTIMIZE=1 (documented in production use)
3. Model uses a cross-encoder architecture (e.g. BERT or RoBERTa with sequence classification)

Coordinated disclosure note: This vulnerability was also reported via huntr.com on April 2, 2026 (https://huntr.com/bounties/dcb05b04-e625-41e7-adbc-bbae0cc2d64c). A GitHub Security Advisory was also filed because it is vLLM's stated preferred disclosure channel per SECURITY.md.

Fix

A fix for this was introduced in this commit: https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3