# langchain_experimental (aka LangChain Experimental) before 0.0.61 for LangChain provides Python REPL access without an opt-in step. NOTE; this issue exists because of an incomplete fix for CVE-2024...

Advisory record · `GHSA-wmvm-9vqv-5qpp`

- **Identifiers:** `GHSA-wmvm-9vqv-5qpp` · `CVE-2024-38459` · `PYSEC-2024-53`
- **State:** Confirmed
- **Severity:** CVSS 7.8 High
- **Critical:** No
- **Weakness (CWE):** [CWE-276](https://cwe.mitre.org/data/definitions/276.html)
- **Tags:** [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 16 Jun 2024
- **Updated:** 10 Jun 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 16 Jun 2024, 15:15 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `langchain-experimental` (PyPI): affected `<ce0b0f22a175139df8f41cdcfb4d2af411112009 || <0.0.61`; fixed in `ce0b0f22a175139df8f41cdcfb4d2af411112009`, `0.0.61`

## Machine-written summary

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

> langchain_experimental versions before 0.0.61 provide Python REPL access without an explicit opt-in step. The source gives few details on what an attacker needs to reach this access, but it can lead to running Python code. Upgrade to langchain_experimental 0.0.61 or later, which fixes this; the source notes the issue stems from an incomplete fix for CVE-2024-27444.

Written 10 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

- 7.8 High, CVSS 3.1: `CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H`, from ADP (CISA-ADP)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0022, the 13th percentile, on 21 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

This record came from the full history of the GitHub Advisory Database, published 16 Jun 2024. New records show when each source confirmed them.

## Sources

- [GitHub Advisory Database: GHSA-wmvm-9vqv-5qpp](https://github.com/advisories/GHSA-wmvm-9vqv-5qpp)
- [OSV: GHSA-wmvm-9vqv-5qpp](https://osv.dev/vulnerability/GHSA-wmvm-9vqv-5qpp)
- <https://github.com/langchain-ai/langchain/pull/22860>
- <https://github.com/langchain-ai/langchain/commit/ce0b0f22a175139df8f41cdcfb4d2af411112009>
- <https://github.com/langchain-ai/langchain/compare/langchain-experimental==0.0.60...langchain-experimental==0.0.61>
- <https://github.com/advisories/GHSA-wmvm-9vqv-5qpp>

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-wmvm-9vqv-5qpp>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-wmvm-9vqv-5qpp/>. Everything for agents: <https://agentprime.io/llms.txt>.
