Home/CVE/vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security chec
CVE
CVE-2026-41523
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security chec
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, 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). This vulnerability is fixed in 0.22.0.
HIGH · CVSS 7.5
Schedule remediation
- CVSS base score ≥ 7.0
No Sigma yet — build one →
YARA rules0
Look this up elsewhere - one-click external pivots
▸
How to read a CVE - triage first, then detect and patch
This page is every public fact about CVE-2026-41523, cross-linked. Its job is to answer one question fast - does this need my attention now? - and then hand you the two things you do about it. Here is how an analyst reads it.
Triage: should I act now? Four signals, and they are not interchangeable:
CVSSseverity - how bad it is IF exploited, 0-10. A high CVSS alone is not urgency; a flaw can be a perfect 10 and never actually be attacked.
EPSSprobability - a model’s estimate of the chance it is exploited in the next 30 days, 0-1. This is the “will it actually happen” signal.
CISA KEVconfirmed - it is being exploited in the wild right now. The strongest signal on the page; KEV beats any score.
Weaponisedavailability - public exploits / PoCs, and especially Metasploit modules rated Excellent / Great. Reliable, packaged exploit code means low-skill attackers can use it today.
How they combine: KEV, or a dependable Metasploit module, means patch now regardless of CVSS. High CVSS + low EPSS + no exploit is real but not an emergency - schedule it. Low CVSS but KEV-listed still gets patched now. The verdict above already weighed these for you; this is how it got there.
Then what - two workflows:
Detectwhen you cannot patch today, follow this CVE to the ATT&CK techniques it enables, then Build a SIEM detection (the green button) - author a rule, test it in Atomic, deploy it. That buys visibility while the patch waits.
PatchAffected products / packages tell you if you are exposed; Fixed versions by distribution and Vendor advisories give the exact version that closes it.
Reading order for the panels below: verdict + badges, then Public exploits / Metasploit (is it weaponised), then ATT&CK techniques + Sigma / IDS rules (can I detect it), then Affected products / packages + Fixed versions (am I exposed, what patches it), then Threat actors / IOCs (who uses it), then Scoring & timeline / references (the evidence).
EPSS exploitation probability
n/a
No EPSS score in our data for this CVE. EPSS is published daily for scored CVEs - a very new, reserved, or rejected CVE may not have one yet.
CVSS metric silhouette
shape grows toward worst-case
SSVC triage
No SSVC vulnrichment for this CVE. CISA's Vulnrichment program scores newer CVEs (~2024 onwards) plus selected older critical ones. Use the EPSS probability + KEV status to triage instead.
CVSS vector breakdown
Exploitability - how they get in
Attack Vector
Network
Adjacent
Local
Physical
Attack Complexity
Low
High
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Impact - what breaks
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
VECTOR
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H◆
ATT&CK techniques
4Techniques this CVE enables. Pills with a solid outline are high confidence - named directly in ATT&CK or Nuclei, or human-curated by CTID; the rest are inferred from the weakness type using MITRE's CVE Mapping Methodology and the CWE → CAPEC chain. Broad, generic-weakness guesses are filtered out. A small N× marks a technique that N independent sources agree on.
T1027.006 · HTML Smuggling T1027.009 · Embedded Payloads T1059 · Command and Scripting Interpreter T1564.009 · Resource Forking
▤ Build a SIEM detection for these techniques
▤
CAPEC attack patterns
3Attack patterns this CVE enables - the bridge from weakness to ATT&CK technique.
⬡
Weakness Classification
▤
Affected Packages
1Language-ecosystem packages (from OSV) tied to this CVE, with the version that fixes it - the dependency-level detail NVD doesn’t carry.
PyPI
vllm
HIGH
fixed in 0.22.0
▤
Related CVEs
8CVEs linked to this one by a shared weakness (CWE) or affected product - joins on data already in the engine, with the reason shown per row. Not a guess.
CVE-2006-4095
BIND before 9.2.6-P1 and 9.3.x before 9.3.2-P1 allows remote attackers to cause ...
same CWE-617
HIGH
CVE-2006-4574
Off-by-one error in the MIME Multipart dissector in Wireshark (formerly Ethereal...
same CWE-617
HIGH
CVE-2006-5779
OpenLDAP before 2.3.29 allows remote attackers to cause a denial of service (dae...
same CWE-617
HIGH
CVE-2006-6811
KsIRC 1.3.12 allows remote attackers to cause a denial of service (crash) via a ...
1
same CWE-617
MEDIUM
CVE-1999-0509
Perl, sh, csh, or other shell interpreters are installed in the cgi-bin director...
same CWE-94
CVE-1999-0491
The prompt parsing in bash allows a local user to execute commands as another us...
1
same CWE-94
CVE-1999-0891
The "download behavior" in Internet Explorer 5 allows remote attackers to read a...
1
same CWE-94
CVE-1999-0702
Internet Explorer 5.0 and 5.01 allows remote attackers to modify or execute file...
1
same CWE-94
🔗
References & Sources
3Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.