# LiteLLM: MCP Proxy Has Improper Authentication

Advisory record · `GHSA-4jcj-7x88-m979`

- **Identifiers:** `GHSA-4jcj-7x88-m979` · `CVE-2026-12773` · `PYSEC-2026-4067`
- **State:** Confirmed
- **Severity:** CVSS 6.9 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-287](https://cwe.mitre.org/data/definitions/287.html) · [CWE-303](https://cwe.mitre.org/data/definitions/303.html)
- **Tags:** [Authentication bypass](https://agentprime.io/advisories/tag/auth-bypass.md)
- **Published:** 21 Jun 2026
- **Updated:** 1 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 21 Jun 2026, 06:32 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `litellm` (PyPI): affected `<1.84.0`; fixed in `1.84.0`

## Machine-written summary

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

> The litellm package before 1.84.0 has improper authentication in its MCP Proxy component. The source gives few details on the exact manipulation, but a remote attacker may be able to exploit it, and a public exploit is available. Upgrade to litellm 1.84.0 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

- 6.9 Medium, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P`, from CNA (VulDB)

- **CISA KEV:** Not listed.
- **EPSS:** 0.010, the 63rd percentile, on 17 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-4jcj-7x88-m979)

## Sources

- [GitHub Advisory Database: GHSA-4jcj-7x88-m979](https://github.com/advisories/GHSA-4jcj-7x88-m979)
- [OSV: GHSA-4jcj-7x88-m979](https://osv.dev/vulnerability/GHSA-4jcj-7x88-m979)
- <https://nvd.nist.gov/vuln/detail/CVE-2026-12773>
- <https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2c>
- <https://access.redhat.com/security/cve/CVE-2026-12773>
- <https://bugzilla.redhat.com/show_bug.cgi?id=2491112>
- <https://gist.github.com/YLChen-007/3cfaad10a69d7a15e4d4d458cb53309e>
- <https://github.com/BerriAI/litellm>
- <https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-12773.json>
- <https://vuldb.com/cve/CVE-2026-12773>
- <https://vuldb.com/submit/811282>
- <https://vuldb.com/vuln/372515>
- <https://vuldb.com/vuln/372515/cti>

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-4jcj-7x88-m979>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-4jcj-7x88-m979/>. Everything for agents: <https://agentprime.io/llms.txt>.
