# vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions

Advisory record · `GHSA-hcwq-8wjf-3gcr`

- **Identifiers:** `GHSA-hcwq-8wjf-3gcr` · `CVE-2026-57173` · `PYSEC-2026-4179`
- **State:** Confirmed
- **Severity:** CVSS 6.5 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-770](https://cwe.mitre.org/data/definitions/770.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 16 Sept 2026
- **Updated:** 1 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 16 Sept 2026, 22:12 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `vllm` (PyPI): affected `<0.24.0`; fixed in `0.24.0`

## Machine-written summary

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

> Unauthenticated remote denial of service in vLLM versions before 0.24.0. The audio decode-duration limit applies only to the speech-to-text endpoint, not to audio sent through /v1/chat/completions. An unauthenticated client can send a small compressed audio file that expands to several gigabytes when decoded, exhausting memory and crashing the worker. Upgrade to vLLM 0.24.0 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

- 6.5 Medium, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0073, the 54th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:09 UTC: First seen by agentprime
- 31 Oct 2026, 14:09 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-hcwq-8wjf-3gcr)

## Sources

- [GitHub Advisory Database: GHSA-hcwq-8wjf-3gcr](https://github.com/advisories/GHSA-hcwq-8wjf-3gcr)
- [OSV: GHSA-hcwq-8wjf-3gcr](https://osv.dev/vulnerability/GHSA-hcwq-8wjf-3gcr)
- <https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-57173>
- <https://github.com/vllm-project/vllm/pull/45908>
- <https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e>
- <https://github.com/vllm-project/vllm>
- <https://github.com/vllm-project/vllm/releases/tag/v0.24.0>

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-hcwq-8wjf-3gcr>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-hcwq-8wjf-3gcr/>. Everything for agents: <https://agentprime.io/llms.txt>.