CVE-2025-68664

Published Dec 23, 2025

Last updated 3 days ago

Overview

AI description

Automated description summarized from trusted sources.

CVE-2025-68664 is a serialization injection vulnerability found in LangChain, a framework used for building agents and LLM-powered applications. The vulnerability exists in versions prior to 0.3.81 and 1.2.5, specifically within the `dumps()` and `dumpd()` functions. These functions fail to properly escape dictionaries containing the `'lc'` key during serialization. The `'lc'` key is used internally by LangChain to identify serialized objects. When user-controlled data includes this key structure, the system incorrectly interprets it as a legitimate LangChain object during deserialization, rather than treating it as plain user data. This can allow attackers to exfiltrate sensitive environment variables and potentially execute code. The vulnerability has been addressed in versions 0.3.81 and 1.2.5.

Description
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, 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. This issue has been patched in versions 0.3.81 and 1.2.5.
Source
security-advisories@github.com
NVD status
Received

Risk scores

CVSS 3.1

Type
Secondary
Base score
9.3
Impact score
4.7
Exploitability score
3.9
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
Severity
CRITICAL

Weaknesses

security-advisories@github.com
CWE-502

Social media

Hype score is a measure of social media activity compared against trending CVEs from the past 12 months. Max score 100.

Hype score

27

  1. 🚨 LangGrinch: Critical LangChain-Core Bug Enables Secret Theft via Serialization Injection (CVE-2025-68664) Attackers can inject crafted `lc`-key objects through user-influenced fields (e.g., `metadata`, `additional_kwargs`, `response_metadata`) so `dumps()/dumpd()` content is

    @ThreatSynop

    27 Dec 2025

    29 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  2. 🚨 Critical LangChain Serialization Injection Bug Exposes Secrets and May Enable Code Execution A critical flaw in langchain-core (CVE-2025-68664) lets attackers inject crafted “lc” structures so user-controlled data is treated as LangChain objects during deserialization,

    @ThreatSynop

    27 Dec 2025

    34 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  3. 🚨 Critical LangChain Flaw Lets Attackers Exfiltrate Secrets via Unsafe Deserialization A critical bug in langchain-core serialization (CVE-2025-68664) enables prompt/LLM-output–influenced data to trigger unsafe deserialization paths (e.g., logging/streaming/caching), leaking

    @ThreatSynop

    27 Dec 2025

    34 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  4. How CVE-2025-68664 Allows Hackers to Siphon Your Private Data Directly from the vLLM Engine Read the full report on - https://t.co/9Aji9Icga9 https://t.co/NeYgkLm8Pj

    @Iambivash007

    27 Dec 2025

    1 Impression

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  5. Critical LangChain Vulnerability (CVE-2025-68664) Puts LLM Apps at Risk #Cybersecurity #cyashadotcom #JanaNayaganAudioLaunch https://t.co/MoAsUFrqjj

    @cyashadotcom

    27 Dec 2025

    341 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  6. CVE-2025-68664: patch LangChain now. Read More: https://t.co/XMxW6mlYZP #Sec #Vuln #Patch #LangChain #Sec #Vuln #Patch #LangChain

    @true_redfence

    27 Dec 2025

    54 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  7. 【LangChain CoreのCVE-2025-68664、修正版公開】 langchain-coreのdumps()/dumpd()で、ユーザー入力に含まれる予約キー「lc」が適切にエスケープされず、load()/loads()でLangChainオブジェクトとして扱われ得る脆弱性(CVE-2025-68664)

    @LangChainJP

    27 Dec 2025

    922 Impressions

    1 Retweet

    7 Likes

    2 Bookmarks

    1 Reply

    0 Quotes

  8. LangChain CVE-2025-68664 (CVSS 9.3) 🚨 ​Prompt Injection is now triggering Deserialization! 🤯 The game has changed. ​Hunters, are you fuzzing lc keys or doing deep Code Review for this? 👇 ​@rez0__ @zwt @nahamsec @Jhaddix @securibee @Rhynorater https://t.co/FZAIXRobD

    @MRTUFAN_BD

    27 Dec 2025

    17 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  9. Falha crítica no LangChain Core permite roubo de segredos e manipulação de respostas: Vulnerabilidade CVE-2025-68664 permite injeção de objetos via serialização, expondo dados sensíveis e possibilitando execuções maliciosas; atualização urgente é recomendada. https:/

    @caveiratech

    26 Dec 2025

    63 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  10. All I Want for Christmas Is Your Secrets: LangGrinch hits LangChain Core (CVE-2025-68664) - Cyata | The Control Plane for Agentic Identity https://t.co/jpzB5SIQXB # #devtalk

    @dev_talk

    26 Dec 2025

    67 Impressions

    0 Retweets

    1 Like

    0 Bookmarks

    0 Replies

    0 Quotes

  11. 🔍 𝐋𝐚𝐭𝐞𝐬𝐭 𝐂𝐕𝐄 𝐛𝐫𝐞𝐚𝐤𝐝𝐨𝐰𝐧 𝐚𝐯𝐚𝐢𝐥𝐚𝐛𝐥𝐞 𝐧𝐨𝐰! Is your LangChain app leaking secrets? Uncover how CVE-2025-68664 enables injection attacks and what steps you must take to secure your AI stack.

    @PurpleOps_io

    26 Dec 2025

    66 Impressions

    0 Retweets

    1 Like

    0 Bookmarks

    0 Replies

    0 Quotes

  12. CVE-2025-68664 - Lord of the Strings: The Return of the 'lc' Key --- In the land of AI agents, so shiny and bright, LangChain was the framework that felt just right. One hundred twenty-three thousand stars in the sky, But nobody noticed the bug slipping by. --- The dumps()

    @gothburz

    26 Dec 2025

    3033 Impressions

    2 Retweets

    32 Likes

    5 Bookmarks

    3 Replies

    1 Quote

  13. Czy jesteś gotów na nową falę zagrożeń cyberbezpieczeństwa dla aplikacji AI? Nowo odkryta podatność w (CVE-2025-68664) osłabia aplikacje AI, umożliwiając kradzież danych i zdalne wykonanie kodu. Bądź na bieżąco! #LangChain #Cybersecurity #AI https://t.co/mjaRQ

    @VIPentest

    26 Dec 2025

    4 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  14. Critical vulnerability in LangChain -- CVE-2025-68664: https://t.co/REzlUDGesF

    @yoshiks

    26 Dec 2025

    3 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  15. A critical LangChain Core vulnerability (CVE-2025-68664) allows attackers to steal secrets and manipulate LLM behavior via serialization injection flaws. https://t.co/bY83uz78PC #CyberSecurity #LangChain #LLMSecurity #PromptInjection #AIThreats #AppSec #CloudSecurity https://t.

    @redsecuretech

    26 Dec 2025

    159 Impressions

    1 Retweet

    2 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  16. 生成AIアプリ基盤として広く使われるLangChainの中核ライブラリに、秘密情報の窃取や応答改変につながる重大な欠陥が判明した(CVE-2025-68664)。巧妙な入力で内部処理を誤作動させ、LLMを攻撃者の意図通りに振る

    @yousukezan

    26 Dec 2025

    2903 Impressions

    12 Retweets

    23 Likes

    20 Bookmarks

    0 Replies

    0 Quotes

  17. #HuttonAIAlerts 🚨 Critical AI Vulnerability Alert 🚨 ​A CVSS 9.3 flaw (CVE-2025-68664) just hit LangChain. Attackers can now exfiltrate your system secrets and API keys via simple prompt injection. ​Your AI "brain" shouldn't be a security liability. (1/4) https://t.co/Y

    @HuttonTech

    26 Dec 2025

    12 Impressions

    7 Retweets

    8 Likes

    0 Bookmarks

    1 Reply

    0 Quotes

  18. LangChain Core has a critical bug that lets attackers extract secrets and steer LLM output. The issue, CVE-2025-68664 (CVSS 9.3), abuses how user data with lc keys is deserialized as trusted objects. Prompt injection can trigger it through normal LLM responses. 🔗 Read → ht

    @TheHackersNews

    26 Dec 2025

    10905 Impressions

    26 Retweets

    76 Likes

    14 Bookmarks

    4 Replies

    2 Quotes

  19. 🚨Vulnerability Alert ‼️ Security researcher Yarden Porat discovered a vulnerability in LangChain that exploits how the framework handles internal serialization markers. The flaw, dubbed CVE-2025-68664, received a CVSS score of 9.3, indicating critical severity. Source:

    @H4ckmanac

    26 Dec 2025

    4762 Impressions

    4 Retweets

    25 Likes

    6 Bookmarks

    1 Reply

    0 Quotes

  20. All I Want for Christmas Is Your Secrets: LangGrinch hits LangChain Core (CVE-2025-68664) https://t.co/uidbKTMqUd

    @NytroRST

    26 Dec 2025

    132 Impressions

    0 Retweets

    1 Like

    1 Bookmark

    0 Replies

    0 Quotes

  21. Today's top 5 cybersecurity news - December 26, 2025 1. A critical vulnerability identified as CVE-2025-68664 has been discovered in LangChain, a widely used AI framework, allowing attackers to extract sensitive environment variable secrets and potentially execute code through a

    @NewsNerdie

    26 Dec 2025

    79 Impressions

    0 Retweets

    1 Like

    0 Bookmarks

    0 Replies

    0 Quotes

  22. LangChain core vuln CVE-2025-68664 allowed env var exfiltration and possible code execution via deserialization flaws, patched just before Christmas 2025. Update now. #Vulnerability https://t.co/sbZrFg791Z

    @threatcluster

    26 Dec 2025

    39 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  23. 🚨 𝐖𝐞 𝐟𝐨𝐮𝐧𝐝 𝐚 𝐜𝐫𝐢𝐭𝐢𝐜𝐚𝐥 𝐯𝐮𝐥𝐧𝐞𝐫𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐢𝐧 𝐋𝐚𝐧𝐠𝐂𝐡𝐚𝐢𝐧. Upgrade to langchain-core 1.2.5 or 0.3.81 immediately. Cyata's security researcher Yarden Porat discovere

    @TeamCyata

    26 Dec 2025

    326 Impressions

    2 Retweets

    8 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  24. 🛡️ Critical Langchain Vulnerability Let Attackers Exfiltrate Sensitive Secrets from AI systems Source: https://t.co/jcmomQRsvF A critical vulnerability in LangChain's core library (CVE-2025-68664) allows attackers to exfiltrate sensitive environment variables and potentia

    @The_Cyber_News

    26 Dec 2025

    2812 Impressions

    14 Retweets

    63 Likes

    18 Bookmarks

    3 Replies

    0 Quotes

  25. Cyata Security Ltd. reports a critical vulnerability in langchain-core, named “LangGrinch” (CVE-2025-68664), endangering AI agent secrets with a CVSS score of 9.3, raising serious security concerns in AI production environments. #LangGrinch #CyberSecurity https://t.co/ynUJLQa

    @Cyber_O51NT

    26 Dec 2025

    1929 Impressions

    74 Retweets

    45 Likes

    1 Bookmark

    0 Replies

    0 Quotes

  26. Merry Christmas... 9.3 Critical... CVE-2025-68664 (Langchain, AI pipelines) https://t.co/FeaZityVrX https://t.co/gw1bBnKxYg

    @JasonGiedymin

    25 Dec 2025

    105 Impressions

    0 Retweets

    2 Likes

    0 Bookmarks

    1 Reply

    0 Quotes

  27. All I Want for Christmas Is Your Secrets: LangGrinch hits LangChain Core (CVE-2025-68664) https://t.co/3WSFrPS0h9

    @jedisct1

    25 Dec 2025

    1340 Impressions

    1 Retweet

    6 Likes

    1 Bookmark

    0 Replies

    0 Quotes

  28. クリスマスに欲しいのはあなたの秘密だけ:LangGrinch が LangChain を攻撃(CVE-2025-68664) All I Want for Xmas Is Your Secrets: LangGrinch Hits LangChain (CVE-2025-68664) https://t.co/C7qlAxJHRf 2025-12-26 05:00:08 +0900

    @hackernewsj

    25 Dec 2025

    11 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  29. ⚠️ LangGrinch (CVE-2025-68664) vole vos secrets LangChain — êtes-vous exposé ? Un bug de sérialisation dans langchain-core permet à une sortie LLM malveillante d’être réhydratée en objet. Risque : extraction de variables d’environnement et instanciation d’obje

    @Eremas8

    25 Dec 2025

    61 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  30. 🚨 CVE-2025-68664 (CVSS 9.3): LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs LangChain is vulnerable to serialization injection. Untrusted data with 'lc' keys can be deserialized as malicious objects, enabling secret extraction vi

    @zoomeye_team

    25 Dec 2025

    5130 Impressions

    12 Retweets

    71 Likes

    27 Bookmarks

    1 Reply

    0 Quotes

  31. LangChain serialization injection (CVE-2025-68664) allows secret extraction via `dumps/loads` APIs. Upgrade to 2e0bed6a21610618b7040cebc6b3b927e120a51a. #LangChain #Security #AI https://t.co/r9px0d5XW5

    @pulsepatchio

    24 Dec 2025

    2 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes

  32. 🚨 CRITICAL: CVE-2025-68664 hits LangChain (<=1.2.4, <0.3.81)! Untrusted deserialization flaw risks code execution & data leaks. Patch to 1.2.5/0.3.81 ASAP! 🔒 Details: https://t.co/TwaZnkzo1T #OffSeq #LangChain... https://t.co/yeS4HSDBT9

    @offseq

    24 Dec 2025

    22 Impressions

    0 Retweets

    0 Likes

    0 Bookmarks

    0 Replies

    0 Quotes