# LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs

Advisory record · `GHSA-c67j-w6g6-q2cm`

- **Identifiers:** `GHSA-c67j-w6g6-q2cm` · `CVE-2025-68664` · `PYSEC-2026-373`
- **State:** Confirmed
- **Severity:** CVSS 9.3 Critical
- **Critical:** Yes: CVSS 9+, CVSS 7+ and EPSS
- **Weakness (CWE):** [CWE-502](https://cwe.mitre.org/data/definitions/502.html)
- **Tags:** [Insecure deserialization](https://agentprime.io/advisories/tag/deserialization.md)
- **Published:** 23 Dec 2025
- **Updated:** 27 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 23 Dec 2025, 18:46 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Critical

Critical, because:

- CVSS score 9.3: 9.0 or more.
- CVSS score 9.3 (7.0 or more) and EPSS 0.43 (0.1 or more): a high score and a real chance of exploitation in the next 30 days.

How we decide what’s critical: <https://agentprime.io/advisories/critical.md>

## Affected packages

- `langchain-core` (PyPI): affected `>=1.0.0, <1.2.5 || <0.3.81`; fixed in `1.2.5`, `0.3.81`

## 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

- 9.3 Critical, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.43, the 98th percentile, on 13 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 23 Dec 2025, 01:44 UTC: [Published by the maintainers as a GitHub repository advisory](https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm)
- 31 Oct 2026, 14:07 UTC: First seen by agentprime
- 31 Oct 2026, 14:07 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-c67j-w6g6-q2cm)

## Sources

- [GitHub Advisory Database: GHSA-c67j-w6g6-q2cm](https://github.com/advisories/GHSA-c67j-w6g6-q2cm)
- [OSV: GHSA-c67j-w6g6-q2cm](https://osv.dev/vulnerability/GHSA-c67j-w6g6-q2cm)
- <https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm>
- <https://nvd.nist.gov/vuln/detail/CVE-2025-68664>
- <https://github.com/langchain-ai/langchain/pull/34455>
- <https://github.com/langchain-ai/langchain/pull/34458>
- <https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8>
- <https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6>
- <https://github.com/langchain-ai/langchain>
- <https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81>
- <https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5>
- <https://github.com/pypa/advisory-database/tree/main/vulns/langchain-core/PYSEC-2026-373.yaml>
- <https://pypi.org/project/langchain-core>

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-c67j-w6g6-q2cm>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-c67j-w6g6-q2cm/>. Everything for agents: <https://agentprime.io/llms.txt>.