Skip to main content
VulnerabilityPublished Updated

CVE-2026-105755: vllm · Insecure Direct Object Reference

Affects vllmSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 4.2 Medium : upgrade to 0.30.0 when convenient.

Data as of 19 Nov 2026, 20:35 UTC

CVSS 3.1 base score
4.2Medium
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (GitHub_M)CVSS 3.14.2
EPSS
0.2% chance of exploitation in 30 days – higher than 10% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 0.30.0
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 5 Oct 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 19 Nov 2026.

What to do

Upgrade vllm and vllm-project/vllm to 0.30.0.

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • <0.30.0
Fixed in
  • 0.30.0
GitHubvllm-project/vllmpkg:github/vllm-project/vllmOther threatsAffected
  • <0.30.0
Fixed in
  • 0.30.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade vLLM to version 0.30.0 or later, where this authorization bypass vulnerability is fixed. No other mitigation is required as the fix addresses the root cause by removing reliance on user-controlled identifiers for query_key derivation.

Description

vLLM versions prior to 0.30.0 have an authorization bypass vulnerability in the /score and /rerank endpoints. The issue arises because the query_key used for scoring is derived from the user-controlled X-Request-Id header. This allows an attacker to reuse a victim's identifier in concurrent requests, causing the victim's documents to be scored against the attacker's query and potentially triggering cache-miss errors. The vulnerability is fixed in version 0.30.0.

References

Community reviews

Loading reviews…