# vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router

Advisory record · `GHSA-hgg8-fqqc-vfmw`

- **Identifiers:** `GHSA-hgg8-fqqc-vfmw` · `CVE-2026-54236` · `PYSEC-2026-3408`
- **State:** Confirmed
- **Severity:** CVSS 5.3 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-532](https://cwe.mitre.org/data/definitions/532.html)
- **Tags:** [Information disclosure](https://agentprime.io/advisories/tag/info-disclosure.md)
- **Published:** 17 Jun 2026
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 17 Jun 2026, 14:04 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.

> The vLLM package, versions before 0.24.0, has an incomplete fix for CVE-2026-22778: several error-handling paths in the Anthropic API router and the realtime speech-to-text WebSocket still return raw exception messages to clients. An attacker who can send requests to these endpoints, such as malformed image content, can get the memory address of a Python object included in the error response, which weakens ASLR protections. Upgrade vLLM to version 0.24.0 or later, which contains the fix.

Written 4 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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0093, the 61st percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:29 UTC: First seen by agentprime
- 31 Oct 2026, 14:29 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-hgg8-fqqc-vfmw)

## Sources

- [GitHub Advisory Database: GHSA-hgg8-fqqc-vfmw](https://github.com/advisories/GHSA-hgg8-fqqc-vfmw)
- [OSV: GHSA-hgg8-fqqc-vfmw](https://osv.dev/vulnerability/GHSA-hgg8-fqqc-vfmw)
- <https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-54236>
- <https://github.com/vllm-project/vllm/pull/45119>
- <https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82>
- <https://github.com/advisories/GHSA-hgg8-fqqc-vfmw>
- <https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3408.yaml>
- <https://github.com/vllm-project/vllm>
- <https://pypi.org/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/GHSA-hgg8-fqqc-vfmw>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-hgg8-fqqc-vfmw/>. Everything for agents: <https://agentprime.io/llms.txt>.
