# vLLM: Public multimodal SHM handle forgery reaches worker-side \`pickle.loads()\` with insecure serialization disabled

Advisory record · `GHSA-6757-hggm-hp2w`

- **Identifiers:** `GHSA-6757-hggm-hp2w` · `CVE-2026-115912` · `PYSEC-2026-4345`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** No
- **Weakness (CWE):** [CWE-502](https://cwe.mitre.org/data/definitions/502.html)
- **Tags:** [Insecure deserialization](https://agentprime.io/advisories/tag/deserialization.md)
- **Published:** 28 Oct 2026
- **Updated:** 29 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 28 Oct 2026, 21:15 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `vllm` (PyPI): affected `<0.32.0`; fixed in `0.32.0`

## Machine-written summary

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

> The vLLM package, versions before 0.32.0, is vulnerable when shared-memory multimodal caching (--mm-processor-cache-type shm) is enabled. An authenticated caller can forge shared-memory handles through public HTTP routes, leading the worker process to call pickle.loads() on attacker-staged bytes, which allows arbitrary Python execution in the worker. Upgrade to vLLM 0.32.0 or later, which contains the fix.

Written 31 Oct 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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0051, the 43rd percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:07 UTC: First seen by agentprime
- 31 Oct 2026, 14:07 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-6757-hggm-hp2w)

## Sources

- [GitHub Advisory Database: GHSA-6757-hggm-hp2w](https://github.com/advisories/GHSA-6757-hggm-hp2w)
- [OSV: GHSA-6757-hggm-hp2w](https://osv.dev/vulnerability/GHSA-6757-hggm-hp2w)
- <https://github.com/vllm-project/vllm/security/advisories/GHSA-6757-hggm-hp2w>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-115912>
- <https://github.com/vllm-project/vllm/pull/59357>
- <https://github.com/vllm-project/vllm/commit/3d5625cc3c2474994107047d7a6ecb8e4008f9b0>
- <https://github.com/vllm-project/vllm>
- <https://github.com/vllm-project/vllm/releases/tag/v0.32.0>

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-6757-hggm-hp2w>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-6757-hggm-hp2w/>. Everything for agents: <https://agentprime.io/llms.txt>.