Last seen March 27, 2026

CVE-2025-68664 Security Incident affecting AI

Evidence indicates that the affected technology is affected by a security issue. Reported affected versions include < 3.0.1.

Technical Severity

Medium severity

Lifecycle Status

DEVELOPING

Sources

2 sources: thehackernews.com +1

What Happened

Evidence indicates that the affected technology is affected by a security issue. Reported affected versions include < 3.0.1.

Why This Matters

Current evidence identifies a security issue involving Critical LangChain Core, but does not yet support a more specific impact claim.

Recommended Action

Upgrade langgraph-checkpoint-sqlite to 3.0.1 or later. Identify deployments of Critical LangChain Core matching the evidenced affected versions: < 3.0.1.

Follow this incident as it develops Material-change notifications are being prepared for BugSkan Pro.

Exposure

Recommended Response

First Seen

Dec 26, 2025 05:30

Last Seen

Mar 27, 2026 05:30

Exploitation status: UNKNOWN

Affected versions: < 3.0.1

Primary entities:

Prompt Injection Remote Code Execution CVE-2025-68664 CVE-2025-67644 CVE-2026-34070 langchain-core

Authoritative Intelligence

CVE CVE-2025-68664, CVE-2025-67644, CVE-2026-34070 Incident identifier

NVD CVSS 7.5 HIGH NVD

FIRST EPSS 0.023 81.5 pct

Fixed Version 3.0.1, 1.2.5, 0.3.81 +1 Provider-backed

GHSA GHSA-9RWJ-6RC7-P77C, GHSA-C67J-W6G6-Q2CM +1 GitHub advisory alias

CWE CWE-22, CWE-89, CWE-502 Weakness classification

Provider evidence: NVD, GitHub Advisory, OSV, FIRST EPSS

EPSS is a vulnerability exploitation probability signal, not proof that your environment is exposed. CISA KEV means known exploitation of the vulnerability, not that your system was exploited.

Timeline

Incident first seen
Dec 26, 2025 05:30
BugSkan first recorded this incident.
Critical LangChain Core Vulnerability Exposes Secrets via Serialization Injection - The Hacker News
Dec 26, 2025 05:30
thehackernews.com · Vulnerability
LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks - The Hacker News
Mar 27, 2026 05:30
thehackernews.com · Vulnerability
Latest observed development
Mar 27, 2026 05:30
Most recent source or update associated with this incident.
Material change
Aug 18, 2026 14:07
recommended action updated
Material change
Aug 18, 2026 14:07
why it matters updated

Sources

Critical LangChain Core Vulnerability Exposes Secrets via Serialization Injection - The Hacker News

thehackernews.com · Dec 26, 2025 05:30

A critical serialization injection vulnerability, CVE-2025-68664, has been discovered in LangChain Core, affecting its `dumps()` and `dumpd()` functions by failing to escape user-controlled dictionaries containing "lc" keys. This flaw allows attackers to instantiate arbitrary objects, potentially leading to secret extraction, prompt injection in LLM responses, and even arbitrary code execution through deserialization.

Open publisher source

LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks - The Hacker News

thehackernews.com · Mar 27, 2026 05:30

Three critical vulnerabilities (CVE-2026-34070, CVE-2025-68664, CVE-2025-67644) have been discovered in LangChain and LangGraph, widely used AI frameworks for building LLM applications. These flaws include path traversal, deserialization of untrusted data, and SQL injection, allowing attackers to access arbitrary filesystem files, leak environment secrets, and execute arbitrary SQL queries against conversation history databases.

Open publisher source

Watchlist Match

Want personalized relevance?

Create an account to see which incidents overlap with the technologies you monitor.