SOURCE-LINKED INTELLIGENCE

GHSA-q8gq-377p-jq3r: vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution

OSV AI package advisories · observation · Jun 16, 2026 · UTC

### 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`](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/layers/pooler/activations.py#L48) as its sole security control to restrict which activation functions can be loaded from a HuggingFace mode

Read original source ↗ Open in workspace

recordType

vulnerability

status

active

evidenceStatus

reported

region

Global