Tuesday, August 11, 2026
LIVEThe Unrelenting Cyber Battle: Hacking Threats and the Imperative of Robust Data Protection///Navigating the Cyber Labyrinth: Bolstering Defenses Against Evolving Hacking Threats///The Dual Front War: Battling Hacking and Bolstering Data Protection in the Digital Age///The Ever-Evolving Cyber Threat Landscape: Navigating Hacking and Fortifying Data Protection///The Unseen Battle: Fortifying Data in an Age of Relentless Hacking///The Unseen War: Hacking's Relentless Advance and the Imperative of Data Protection///The Evolving Threat Landscape: Hacking, Data Protection, and the Imperative for Proactive Security///Navigating the Digital Minefield: Bolstering Data Protection in an Era of Relentless Hacking///The Dual Fronts of Digital Defense: Combating Hacking and Fortifying Data Protection///Hacking's New Frontier: Fortifying Data Protection in the Age of Advanced Cyber Threats///The Dual Front: Navigating Hacking Threats and Fortifying Data Protection in the Digital Age///Navigating the Digital Gauntlet: The Evolving Nexus of Hacking and Data Protection///The Unrelenting Cyber Battle: Hacking Threats and the Imperative of Robust Data Protection///Navigating the Cyber Labyrinth: Bolstering Defenses Against Evolving Hacking Threats///The Dual Front War: Battling Hacking and Bolstering Data Protection in the Digital Age///The Ever-Evolving Cyber Threat Landscape: Navigating Hacking and Fortifying Data Protection///The Unseen Battle: Fortifying Data in an Age of Relentless Hacking///The Unseen War: Hacking's Relentless Advance and the Imperative of Data Protection///The Evolving Threat Landscape: Hacking, Data Protection, and the Imperative for Proactive Security///Navigating the Digital Minefield: Bolstering Data Protection in an Era of Relentless Hacking///The Dual Fronts of Digital Defense: Combating Hacking and Fortifying Data Protection///Hacking's New Frontier: Fortifying Data Protection in the Age of Advanced Cyber Threats///The Dual Front: Navigating Hacking Threats and Fortifying Data Protection in the Digital Age///Navigating the Digital Gauntlet: The Evolving Nexus of Hacking and Data Protection///
Subscribe
Cyber Security
Independent · Digital
Thehackingpost
RSSSubscribe
CybersecurityAI-assisted

Critical LangChain Vulnerability Allows Attackers to Steal Sensitive Secrets

## Cybersecurity Update: LangChain Vulnerability CVE-2025-68664

ABy Allison BurkeDec 27, 20251 min read

Cybersecurity Update: LangChain Vulnerability CVE-2025-68664

A critical security vulnerability has been identified in LangChain, a widely utilized AI framework. This vulnerability, known as CVE-2025-68664, allows attackers to extract environment variable secrets and possibly achieve code execution through a serialization injection flaw.

The issue arises from improper handling of serialization functions, dumps() and dumpd() , in the langchain-core library. This vulnerability was disclosed on Tue, Dec 25, 2024, by security researcher Yarden Porat from Cyata.

Attribute Details

CVE ID CVE-2025-68664

GHSA ID GHSA-c67j-w6g6-q2cm

A critical security vulnerability has been identified in LangChain, a widely utilized AI framework.
Allison Burke · Thehackingpost

CVSS Score 9.3 (Critical)

The vulnerability affects applications using standard LangChain features, including astream_events(version="v1") , Runnable: astream_log() , RunnableWithMessageHistory , and various caching mechanisms. The most severe attack vector involves prompt injection via LLM response fields, such as additional_kwargs or response_metadata , which can be serialized and deserialized through standard streaming operations.

Successful exploitation allows attackers to extract environment variable secrets by injecting structures like {"lc": 1, "type": "secret", "id": ["ENV_VAR"]} during deserialization, especially when secrets_from_env=True (the previous default setting).

LangChain has released patches in versions 1.2.5 and 0.3.81 to address this issue. The updates fix the escaping bug and introduce restrictive defaults. The allowed_objects parameter now defaults to 'core', limiting deserialization to core objects. Additionally, secrets_from_env has changed from True to False , and Jinja2 templates are now blocked by default through a new init_validator parameter.

Advertisement

Organizations using LangChain in production are advised to update immediately, as the framework has recorded approximately 847 million total downloads, including 98 million in the last month alone.

LangChain awarded a $4,000 bounty for this finding, marking the highest reward ever offered by the project.

Based on reporting by GBHackers.

AI transparency. This article was produced with the assistance of artificial intelligence and published under human editorial oversight. AI systems can make mistakes. Read how we use AI (EU AI Act, Art. 50).
Related Stories
Cybersecurity

Why Fintech Banking Platforms Are Reducing Operational Costs by 40%

Paige Monroe · Mar 26, 2026
Cybersecurity

Dogecoin Price Prediction: SHIB Burns 172M Tokens as Pepeto Exchange Earns From Every Trade

Eric Wallace · Mar 26, 2026
Cybersecurity

Solana Price Prediction: SOL Holds $86 With Commodity Status as Pepeto Targets Bigger Returns

Zachary Burns · Mar 26, 2026
Cybersecurity

Open Directory Malware Campaign Uses Obfuscated VBS, PNG Loaders and RAT Payloads

Joseph Cain · Mar 26, 2026