Home/CVE/vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning contr
CVE
CVE-2026-47155
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning contr
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision.
This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.
MEDIUM · CVSS 6.5
Monitor
- No active-exploitation, high-EPSS, or public-exploit signals - routine patching cadence
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-2026-47155, 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:N/S:U/C:L/I:H/A:N◆
ATT&CK techniques
1Techniques 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.
▤ Build a SIEM detection for these techniques▤
CAPEC attack patterns
12Attack patterns this CVE enables - the bridge from weakness to ATT&CK technique.
CAPEC-CAPEC-111 · JSON Hijacking (aka JavaScript Hijacking) CAPEC-CAPEC-141 · Cache Poisoning CAPEC-CAPEC-142 · DNS Cache Poisoning CAPEC-CAPEC-148 · Content Spoofing CAPEC-CAPEC-218 · Spoofing of UDDI/ebXML Messages CAPEC-CAPEC-384 · Application API Message Manipulation via Man-in-the-Middle CAPEC-CAPEC-385 · Transaction or Event Tampering via Application API Manipulation CAPEC-CAPEC-386 · Application API Navigation Remapping CAPEC-CAPEC-387 · Navigation Remapping To Propagate Malicious Content CAPEC-CAPEC-388 · Application API Button Hijacking CAPEC-CAPEC-665 · Exploitation of Thunderbolt Protection Flaws CAPEC-CAPEC-701 · Browser in the Middle (BiTM)
⬡
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
MODERATE
fixed in 0.22.0
▤
Related CVEs
4CVEs 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-2013-7397
Async Http Client (aka AHC or async-http-client) before 1.9.0 skips X.509 certif...
same CWE-345
CVE-2013-7398
main/java/com/ning/http/client/AsyncHttpClientConfig.java in Async Http Client (...
same CWE-345
CVE-2013-2167
python-keystoneclient version 0.2.3 to 0.2.5 has middleware memcache signing byp...
same CWE-345
CRITICAL
CVE-2014-0364
The ParseRoster component in the Ignite Realtime Smack XMPP API before 4.0.0-rc1...
same CWE-345
🔗
References & Sources
4Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.