# vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 M...

Advisory record · `GHSA-p6g9-7v3x-m8mv`

- **Identifiers:** `GHSA-p6g9-7v3x-m8mv` · `CVE-2026-100650` · `PYSEC-2026-4184`
- **State:** Confirmed
- **Severity:** CVSS 7.1 High
- **Critical:** No
- **Weakness (CWE):** [CWE-400](https://cwe.mitre.org/data/definitions/400.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 26 Sept 2026
- **Updated:** 7 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 26 Sept 2026, 14:16 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `vllm` (PyPI): affected `<0.30.0`; fixed in `0.30.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> vLLM through 0.29.0 reads entire remote or inline media (audio, images and similar) into memory before checking its documented size and item limits, including the audio size cap and per-prompt item limits. A remote attacker who can reach the API server, batch runner or Rust frontend /tokenize route can send oversized or numerous media to exhaust memory and bandwidth, causing denial of service. The chat and batch endpoints require an API key when one is configured, while /tokenize does not. Upgrade to vLLM 0.30.0 or later.

Written 1 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 7.1 High, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N`, from CNA (VulnCheck)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0081, the 57th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:08 UTC: First seen by agentprime
- 31 Oct 2026, 14:08 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/PYSEC-2026-4184)

## Sources

- [GitHub Advisory Database: GHSA-p6g9-7v3x-m8mv](https://github.com/advisories/GHSA-p6g9-7v3x-m8mv)
- [OSV: GHSA-p6g9-7v3x-m8mv](https://osv.dev/vulnerability/GHSA-p6g9-7v3x-m8mv)
- <https://www.vulncheck.com/advisories/vllm-before-0.29.0-resource-exhaustion-via-unbounded-media-materialization>
- <https://github.com/vllm-project/vllm/commit/752a3a504485790a2e8491cacbb35c137339ad34>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-p6g9-7v3x-m8mv>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-p6g9-7v3x-m8mv/>. Everything for agents: <https://agentprime.io/llms.txt>.