vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)
CVSS score
6.5
EPSS probability
%0.3
Risk score
0.0
Published
7 d ago
Etkilenen ürün ve sürüm için yayımlanan güvenlik güncellemesini uygulayın.
Impact on My Inventory
Only the personal products you have added to your account are assessed; an organisation's inventory does not appear here.
Checking session…
Vulnerability description
DayBreach CVE AI Research
CVE-2026-105757 has vendor, distribution, patch and security-source records on file. We can compare them and prepare an explanation linked to the evidence.
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.
IMPACT: Affected Products and Software
RED HAT CSAF/VEX: Product Impact Check
SCORING: CVSS from Multiple Sources
CVSS Scores
The Common Vulnerability Scoring System is a standardised framework for assessing the severity of vulnerabilities in software and systems. We collect and display CVSS scores from several sources for each CVE.
| SCORE | VERSION | SEVERITY | VECTOR | SOURCE |
|---|---|---|---|---|
| 6.5 | CVSS 3.x | — | Vector not published | GitHub Advisory |
| 6.5 | CVSS V3_1 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CVE CNA |
| 6.5 | CVSS V31 | MEDIUM | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | NVD |
| 0.0 | CVSS 4.0 | — | Vector not published | GitHub Advisory |
Patch and Remediation Guide
Solution & Remediation Advisory
3 doğrulanmış yama veya düzeltilmiş sürüm kanıtı bulundu.
0.30.0OSV düzeltilmiş sürüm: 0.30.0
Public exploit and active exploitation status
Verified exploit intelligence
No verified public PoC, exploit repository or Metasploit module has been found for this CVE yet.
Weakness Classification and Attack Patterns (CWE & CAPEC)
CWE - Common Weakness Enumeration
While CVE identifies specific instances of vulnerabilities, CWE categorises the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-105757 is associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-105757 weaknesses.
Attack Vector and Accessibility
Official Sources and Advisories
Similar Vulnerabilities
MLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebinding)
Vulnerability in Vllm
SQL injection in Litellm
netlicensing-mcp: REST Path Traversal Bypasses Token Redaction
Starlette has missing Host header validation that poisons request.url.path, bypassing path-based security checks
ESPHome Device Builder Dashboard: Unauthenticated dashboard access via the HA add-on ingress site bound to all interfaces
Get this vulnerability through the API
Affected products, version ranges, exploitation status and patch information in a single request, with a free key.
curl -H "x-api-key: $DAYBREACH_API_KEY" \ "https://api.enginteksut.com.tr/api/v1/intel/cves/CVE-2026-105757"