[UPDATE] [medium] vllm: Vulnerability allows code execution

mediumCVE-2026-41523

A remote, anonymous attacker can exploit a vulnerability in vllm to execute arbitrary code.

CSIRTS triage

vendor: vllm product: vllm Remote code execution

What: A vulnerability allows a remote, anonymous attacker to execute arbitrary code.
Who is affected: Deployments of vllm are affected.
Urgency: Remediation is medium urgency as the vulnerability can lead to remote code execution.
Action: Update to the latest version of vllm.

AI-assisted analysis generated from the source advisory — verify against the original.

⚡ Watch vllm

Get an email when a new vllm advisory drops — max one per day, one-click unsubscribe.

Details

Source: CERT-Bund (BSI) Security Advisories (DE · national-cert · site)
Severity: medium
Published: 2026-09-02
Exploitation: Not in CISA KEV at last sync
Language: Machine-translated to English — verify against the original

Original advisory: https://wid.cert-bund.de/portal/wid/securityadvisory?name=WID-SEC-2026-1911

Exploitation outlook

EPSS (FIRST.org) estimates each CVE’s probability of exploitation in the next 30 days — here is the CSIRTS.com read on those numbers.

Low exploitation riskCVE-2026-415230.88% 30-day exploitation probability — currently an unlikely target, but scores change as exploit code circulates. Riskier than 56% of all EPSS-scored CVEs.

Referenced CVEs

CVE	CSIRTS overview	External
CVE-2026-41523	coverage & exploitation status	NVD · CVE.org

Same CVEs, other sources

How other CERTs, PSIRTs and databases cover the vulnerabilities in this advisory.

highGHSA-q8gq-377p-jq3r: vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Ar…ghsa

Recent advisories for vllm

A cluster of recent advisories against the same product widens the attack surface — attackers routinely chain freshly published CVEs on one product, so review these together.

mediumGHSA-pr7f-p5mw-fc87: vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt partsghsa · 2026-09-04
mediumGHSA-48jh-3gj7-fg8v: vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile ti…ghsa · 2026-09-04
mediumGHSA-hwrm-c4cx-rf4j: vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messagesghsa · 2026-09-04
mediumGHSA-8737-qx52-hjff: vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output…ghsa · 2026-09-04
medium[NEU] [mittel] vllm: Schwachstelle ermöglicht Denial of Servicecert-bund · 2026-09-04
medium[UPDATE] [medium] vllm: Multiple vulnerabilitiescert-bund · 2026-09-02