Skip to content
Patch Next
Sign inAdd to your agent

← Actionable
Critical, CVSS 9.3amended

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

CVE-2025-68664GHSA-c67j-w6g6-q2cm

What to do

Vendor fix available. Upgrade each affected package to the fixed version on its release line (langchain-core 1.2.5, 0.3.81), redeploy, then verify what is actually installed.

This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.

Add to your agent

Affected packages

  • PyPI langchain-core

    Affected
    >= 1.0.0, < 1.2.5< 0.3.81
    Fixed in
    0.3.81, 1.2.5

Sources

Severity and exploitation
Exploitation
No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
CVSS
9.3 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
EPSS
  • CVE-2025-68664: 42.93% estimated exploitation activity in the next 30 days; percentile 98.72 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description

As published by the source; long descriptions are shortened.

Summary A serialization injection vulnerability exists in LangChain's `dumps()` and `dumpd()` functions. The functions do not escape dictionaries with `'lc'` keys when serializing free-form dictionaries. The `'lc'` key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data.

Attack surface The core vulnerability was in `dumps()` and `dumpd()`: these functions failed to escape user-controlled dictionaries containing `'lc'` keys. When this unescaped data was later deserialized via `load()` or `loads()`, the injected structures were treated as legitimate LangChain objects rather than plain user data. This escaping bug enabled several attack vectors: 1. Injection via user data: Malicious LangChain object structures could be injected through user-controlled fields like `metadata`, `additional_kwargs`, or `response_metadata`…

Dates and revisions
Published by the source
Last modified by the source
Source last checked
  1. Revision 5 · amended ·

    Amended from osv record GHSA-c67j-w6g6-q2cm

  2. Revision 4 · amended ·

    Amended from ghsa record GHSA-c67j-w6g6-q2cm

  3. Revision 3 · amended ·

    Amended from ghsa record GHSA-c67j-w6g6-q2cm

  4. Revision 2 · amended ·

    Amended from osv record GHSA-c67j-w6g6-q2cm

  5. Revision 1 · created ·

    Published from ghsa record GHSA-c67j-w6g6-q2cm

Agent brief

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2025-68664

Advisory: LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
IDs: CVE-2025-68664, GHSA-c67j-w6g6-q2cm
Record: https://patchnext.com/advisories/cve-2025-68664 (revision 5, source checked 28 Oct 2026, 06:05 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Critical (CVSS 9.3)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: langchain-core 1.2.5, 0.3.81. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI langchain-core: affected >= 1.0.0, < 1.2.5; < 0.3.81; fixed in 0.3.81, 1.2.5

## Suggested inspection (read-only)
- `python -m pip show langchain-core`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on langchain-core.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-c67j-w6g6-q2cm (GitHub-reviewed advisory GHSA-c67j-w6g6-q2cm lists affected ranges: PyPI langchain-core >=1.0.0 =0 <0.3.81)
- Verified: https://osv.dev/vulnerability/GHSA-c67j-w6g6-q2cm (OSV record GHSA-c67j-w6g6-q2cm lists affected ranges: PyPI langchain-core >=1.0.0 =0 <0.3.81 (fixed))

Commands are suggestions: review each one before running it.

Loading voting…