# vLLM through 0.29.0 fails to properly clean up decode-side metadata for rejected inference requests in prefill/decode disaggregated deployments. Remote attackers can submit requests with max_tokens...

Advisory record · `PYSEC-2026-3996`

- **Identifiers:** `PYSEC-2026-3996` · `CVE-2026-93436`
- **State:** Confirmed
- **Severity:** CVSS 8.7 High
- **Critical:** No
- **Weakness (CWE):** [CWE-401](https://cwe.mitre.org/data/definitions/401.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 17 Sept 2026
- **Updated:** 29 Sept 2026
- **Reviewed by a person:** No

Published by OSV at 17 Sept 2026, 23:18 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`

## 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

- 8.7 High, CVSS 4.0: `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`, from CNA (VulnCheck)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0076, the 55th percentile, on 13 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/PYSEC-2026-3996)

## Sources

- [OSV: PYSEC-2026-3996](https://osv.dev/vulnerability/PYSEC-2026-3996)
- <https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/distributed/kv_transfer/kv_connector/v1/nixl/push_worker.py#L162-L181>
- <https://www.vulncheck.com/advisories/vllm-through-0.29.0-memory-exhaustion-via-rejected-requests>
- <https://github.com/vllm-project/vllm/pull/55677>
- <https://github.com/vllm-project/vllm>

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/PYSEC-2026-3996>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/PYSEC-2026-3996/>. Everything for agents: <https://agentprime.io/llms.txt>.