All vulnerabilities

Servers and applications

CVE-2026-41523

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

Severity
High 7.5
Published
14 Jun 2026
Last changed
25 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.22.0
Exploit chance
0.9% in the next 30 daysHigher than 60% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Code injection (CWE-94)CWE-617
Attack
Over the network · Only under certain conditions · No login needed · Needs someone to click or open something
Attacker can
Read data · Change data · Take it down
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Also known as
GHSA-q8gq-377p-jq3r
Sources
NVD, Project advisories (GitHub)

Description

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).

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:

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:

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…

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.22.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.22.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-41523
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-41523
  • GitHub Advisory Database https://github.com/advisories/GHSA-q8gq-377p-jq3r
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-q8gq-377p-jq3r