# LiteLLM Vulnerable to Remote Code Execution (RCE)

Advisory record · `GHSA-53gh-p8jc-7rg8`

- **Identifiers:** `GHSA-53gh-p8jc-7rg8` · `CVE-2024-6825` · `PYSEC-2026-1541`
- **State:** Confirmed
- **Severity:** CVSS 8.8 High
- **Critical:** No
- **Weakness (CWE):** [CWE-77](https://cwe.mitre.org/data/definitions/77.html) · [CWE-94](https://cwe.mitre.org/data/definitions/94.html)
- **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md) · [Code injection](https://agentprime.io/advisories/tag/code-injection.md)
- **Published:** 20 Mar 2025
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 20 Mar 2025, 12:32 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `litellm` (PyPI): affected `>=1.40.3.dev2, <=1.40.12`; no fixed version yet

## Machine-written summary

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

> LiteLLM versions >=1.40.3.dev2 through 1.40.12 are vulnerable to remote code execution through the post_call_rules configuration, which accepts a callback function that is loaded by splitting its value at the final dot. An attacker who can set this configuration value could point it at a system function such as os.system, causing arbitrary commands to run when a chat response is processed. No fixed version is listed in the source.

Written 5 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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.017, the 76th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:37 UTC: First seen by agentprime
- 31 Oct 2026, 14:37 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-53gh-p8jc-7rg8)

## Sources

- [GitHub Advisory Database: GHSA-53gh-p8jc-7rg8](https://github.com/advisories/GHSA-53gh-p8jc-7rg8)
- [OSV: GHSA-53gh-p8jc-7rg8](https://osv.dev/vulnerability/GHSA-53gh-p8jc-7rg8)
- <https://nvd.nist.gov/vuln/detail/CVE-2024-6825>
- <https://github.com/berriai/litellm/commit/441c7275ed2715f47650a7c2e525055c804073a9>
- <https://github.com/BerriAI/litellm>
- <https://github.com/BerriAI/litellm/blob/056913fd7049923a106130b02d7c29e7f312beec/litellm/utils.py#L2818>
- <https://huntr.com/bounties/1d98bebb-6cf4-46c9-87c3-d3b1972973b5>

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-53gh-p8jc-7rg8>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-53gh-p8jc-7rg8/>. Everything for agents: <https://agentprime.io/llms.txt>.
