AI safety & securitymedium
LangChain core vulnerability allows prompt injection and data exposure
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-68664 | Serialization Injection in LangChain Core dumps()/dumpd() Exposes Secrets | 8.2 | 43% | PoC ×2 |
From the original article
2 min read at securityaffairs.com
A critical flaw in LangChain Core could allow attackers to steal sensitive secrets and manipulate LLM responses via prompt injection. LangChain Core ( langchain-core ) is a key Python package in the LangChain ecosystem that provides core interfaces and model-agnostic tools for building LLM-based applications. A critical vulnerability, tracked as CVE-2025-68664 (CVSS score of 9.
By @securityaffairs · securityaffairs.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.