# LiteLLM: Arbitrary file write via path traversal in Skills archive extraction

Advisory record · `GHSA-5jmr-gcrj-2c9q`

- **Identifiers:** `GHSA-5jmr-gcrj-2c9q` · `CVE-2026-59820` · `PYSEC-2026-3477`
- **State:** Confirmed
- **Severity:** CVSS 6.1 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-22](https://cwe.mitre.org/data/definitions/22.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, 22:37 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `litellm` (PyPI): affected `<1.83.7`; fixed in `1.83.7`

## Machine-written summary

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

> LiteLLM versions before 1.83.7 are vulnerable to arbitrary file write via path traversal during Skills archive extraction. An authenticated user with access to LiteLLM API routes, or a key permitted to reach /v1/skills, anthropic_routes, or llm_api_routes, can upload a crafted skill ZIP archive whose path traversal entries are written outside the staging directory, potentially leading to code execution. Upgrade to 1.83.7-stable or later; if upgrading is not possible, block POST /v1/skills at a reverse proxy or restrict Skills API access to trusted users.

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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0059, the 48th 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-5jmr-gcrj-2c9q)

## Sources

- [GitHub Advisory Database: GHSA-5jmr-gcrj-2c9q](https://github.com/advisories/GHSA-5jmr-gcrj-2c9q)
- [OSV: GHSA-5jmr-gcrj-2c9q](https://osv.dev/vulnerability/GHSA-5jmr-gcrj-2c9q)
- <https://github.com/BerriAI/litellm/security/advisories/GHSA-5jmr-gcrj-2c9q>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-59820>
- <https://github.com/BerriAI/litellm/pull/25475>
- <https://github.com/BerriAI/litellm/commit/6a15adcd64137d37f73dee76dfe7481f8c2d9196>
- <https://github.com/BerriAI/litellm>
- <https://github.com/BerriAI/litellm/releases/tag/v1.83.7-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-5jmr-gcrj-2c9q>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-5jmr-gcrj-2c9q/>. Everything for agents: <https://agentprime.io/llms.txt>.
