# LiteLLM Server-Side Request Forgery (SSRF) vulnerability

Advisory record · `GHSA-g26j-5385-hhw3`

- **Identifiers:** `GHSA-g26j-5385-hhw3` · `CVE-2024-6587` · `PYSEC-2026-1547`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** Yes: CVSS 7+ and EPSS
- **Weakness (CWE):** [CWE-918](https://cwe.mitre.org/data/definitions/918.html)
- **Tags:** [Server-side request forgery (SSRF)](https://agentprime.io/advisories/tag/ssrf.md)
- **Published:** 13 Sept 2024
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 13 Sept 2024, 18:31 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 7.5 (7.0 or more) and EPSS 0.34 (0.1 or more): a high score and a real chance of exploitation in the next 30 days.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `litellm` (PyPI): affected `<1.44.8`; fixed in `1.44.8`

## Machine-written summary

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

> LiteLLM versions before 1.44.8 are vulnerable to server-side request forgery. An attacker who can send requests to the POST /chat/completions endpoint can set the api_base parameter to a domain they control, causing the server to send the request, including the OpenAI API key, to that domain. Upgrade litellm to version 1.44.8 or later.

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

- 7.5 High, CVSS 3.0: `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N`, from CNA (@huntr_ai)

- **CISA KEV:** Not listed.
- **EPSS:** 0.34, the 98th percentile, on 15 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-g26j-5385-hhw3)

## Sources

- [GitHub Advisory Database: GHSA-g26j-5385-hhw3](https://github.com/advisories/GHSA-g26j-5385-hhw3)
- [OSV: GHSA-g26j-5385-hhw3](https://osv.dev/vulnerability/GHSA-g26j-5385-hhw3)
- <https://nvd.nist.gov/vuln/detail/CVE-2024-6587>
- <https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0>
- <https://github.com/berriai/litellm>
- <https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997>

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-g26j-5385-hhw3>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-g26j-5385-hhw3/>. Everything for agents: <https://agentprime.io/llms.txt>.
