# LiteLLM: Admin Key Handler Has Improper Authorization

Advisory record · `GHSA-6qr3-3g89-m4jj`

- **Identifiers:** `GHSA-6qr3-3g89-m4jj` · `CVE-2026-12770` · `PYSEC-2026-4068`
- **State:** Confirmed
- **Severity:** CVSS 5.3 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-266](https://cwe.mitre.org/data/definitions/266.html) · [CWE-285](https://cwe.mitre.org/data/definitions/285.html)
- **Tags:** [Privilege escalation](https://agentprime.io/advisories/tag/privilege-escalation.md) · [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 21 Jun 2026
- **Updated:** 1 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 21 Jun 2026, 03:30 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `litellm` (PyPI): affected `<=1.63.1`; no fixed version yet

## Machine-written summary

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

> The litellm package, versions up to and including 1.63.1, has an improper authorization flaw in its Admin Key Handler. The source gives few details on the exact conditions. A remote attacker may be able to exploit it, and a public exploit has been disclosed. No fix is listed.

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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0057, the 47th percentile, on 15 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-6qr3-3g89-m4jj)

## Sources

- [GitHub Advisory Database: GHSA-6qr3-3g89-m4jj](https://github.com/advisories/GHSA-6qr3-3g89-m4jj)
- [OSV: GHSA-6qr3-3g89-m4jj](https://osv.dev/vulnerability/GHSA-6qr3-3g89-m4jj)
- <https://nvd.nist.gov/vuln/detail/CVE-2026-12770>
- <https://github.com/BerriAI/litellm/pull/23781>
- <https://gist.github.com/YLChen-007/993c68152b2c770d53590f1684c755d4>
- <https://github.com/BerriAI/litellm>
- <https://vuldb.com/cve/CVE-2026-12770>
- <https://vuldb.com/submit/811279>
- <https://vuldb.com/vuln/372512>
- <https://vuldb.com/vuln/372512/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-6qr3-3g89-m4jj>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-6qr3-3g89-m4jj/>. Everything for agents: <https://agentprime.io/llms.txt>.