# LiteLLM: Local file read via request-supplied OIDC file references

Advisory record · `GHSA-4g5m-c9r5-49xf`

- **Identifiers:** `GHSA-4g5m-c9r5-49xf` · `CVE-2026-59819` · `PYSEC-2026-3476`
- **State:** Confirmed
- **Severity:** CVSS 2.1 Low
- **Critical:** No
- **Weakness (CWE):** [CWE-73](https://cwe.mitre.org/data/definitions/73.html)
- **Tags:** [Path traversal](https://agentprime.io/advisories/tag/path-traversal.md)
- **Published:** 22 Jul 2026
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 22 Jul 2026, 22:38 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `litellm` (PyPI): affected `<1.83.10`; fixed in `1.83.10`

## Machine-written summary

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

> LiteLLM versions before 1.83.10 are affected. The /health/test_connection endpoint resolved request-supplied OIDC file references, so a privileged caller with permission to test model connections, such as a proxy administrator, could make LiteLLM read local files. Upgrade to LiteLLM 1.83.10 or later. Until then, restrict access to /health/test_connection to trusted administrators only.

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

- 2.1 Low, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:P/PR:H/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N`, from CNA (GitHub_M)

- **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, 14:11 UTC: First seen by agentprime
- 31 Oct 2026, 14:11 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-4g5m-c9r5-49xf)

## Sources

- [GitHub Advisory Database: GHSA-4g5m-c9r5-49xf](https://github.com/advisories/GHSA-4g5m-c9r5-49xf)
- [OSV: GHSA-4g5m-c9r5-49xf](https://osv.dev/vulnerability/GHSA-4g5m-c9r5-49xf)
- <https://github.com/BerriAI/litellm/security/advisories/GHSA-4g5m-c9r5-49xf>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-59819>
- <https://github.com/BerriAI/litellm/pull/25592>
- <https://github.com/BerriAI/litellm>
- <https://github.com/BerriAI/litellm/releases/tag/v1.83.10-stable>

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-4g5m-c9r5-49xf>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-4g5m-c9r5-49xf/>. Everything for agents: <https://agentprime.io/llms.txt>.
