{"id":228096,"date":"2026-03-27T04:07:00","date_gmt":"2026-03-27T08:07:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/03\/27\/langchain-langgraph-flaws-expose-files-secrets-databases-in-widely-used-ai-frameworks\/"},"modified":"2026-03-27T06:45:08","modified_gmt":"2026-03-27T10:45:08","slug":"langchain-langgraph-flaws-expose-files-secrets-databases-in-widely-used-ai-frameworks","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/03\/27\/langchain-langgraph-flaws-expose-files-secrets-databases-in-widely-used-ai-frameworks\/","title":{"rendered":"LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks"},"content":{"rendered":"<p><a href=\"https:\/\/thehackernews.com\/2026\/03\/langchain-langgraph-flaws-expose-files.html\">LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks<\/a><\/p>\n<p><a href=\"https:\/\/thehackernews.com\/2026\/03\/langchain-langgraph-flaws-expose-files.html\">https:\/\/thehackernews.com\/2026\/03\/langchain-langgraph-flaws-expose-files.html<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-03-27 04:07:00<\/a><\/p>\n<p>Source Domain: <a href=\"thehackernews.com\">thehackernews.com<\/a><\/p>\n<p><span class=\"p-author\">\ue804<span class=\"author\">Ravie Lakshmanan<\/span>\ue802<span class=\"author\">Mar 27, 2026<\/span><\/span><span class=\"p-tags\">Vulnerability \/ Artificial Intelligence<\/span><\/p>\n<p>Cybersecurity researchers have disclosed three security vulnerabilities impacting LangChain and LangGraph that, if successfully exploited, could expose filesystem data, environment secrets, and conversation history.<\/p>\n<p>Both LangChain and LangGraph are open-source frameworks that are used to build applications powered by Large Language Models (LLMs). LangGraph is built on the foundations of LangChain for more sophisticated and non-linear agentic workflows. According to statistics on the Python Package Index (PyPI), LangChain, LangChain-Core, and LangGraph have been downloaded more than 52 million, 23 million, and 9 million times last week alone.<\/p>\n<p>&#8220;Each vulnerability exposes a different class of enterprise data: filesystem files, environment secrets, and conversation history,&#8221; Cyera security researcher Vladimir Tokarev said in a report published Thursday.<\/p>\n<p>The issues, in a nutshell, offer three independent paths that an attacker can leverage to drain sensitive data from any enterprise LangChain deployment. Details of the vulnerabilities are as follows &#8211;<\/p>\n<ul>\n<li><strong>CVE-2026-34070<\/strong> (CVSS score: 7.5) &#8211; A path traversal vulnerability in LangChain (&#8220;langchain_core\/prompts\/loading.py&#8221;) that allows access to arbitrary files without any validation via its prompt-loading API by supplying a specially crafted prompt template.<\/li>\n<li><strong>CVE-2025-68664<\/strong> (CVSS score: 9.3) &#8211; A deserialization of untrusted data vulnerability in LangChain that leaks API keys and environment secrets by passing as input a data structure that tricks the application into interpreting it as an already serialized LangChain object rather than regular user data.<\/li>\n<li><strong>CVE-2025-67644<\/strong> (CVSS score: 7.3) &#8211; An SQL injection vulnerability in LangGraph SQLite checkpoint implementation that allows an attacker to manipulate SQL queries through metadata filter keys and run arbitrary SQL queries against the database.<\/li>\n<\/ul>\n<p>Successful exploitation of the aforementioned flaws&#8230;<\/p>\n<p><a href=\"https:\/\/thehackernews.com\/2026\/03\/langchain-langgraph-flaws-expose-files.html\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>LangChain, LangGraph Flaws Expose Files, Secrets, Databases in Widely Used AI Frameworks https:\/\/thehackernews.com\/2026\/03\/langchain-langgraph-flaws-expose-files.html Publish Date:&#8230;<\/p>\n","protected":false},"author":1,"featured_media":228097,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/blogger.googleusercontent.com\/img\/b\/R29vZ2xl\/AVvXsEgkhroYg33geYKogEf838RfX0FRNjBX23ucPFzrxtbtf2CyTxoGZZ4RbTArZX672fygWxhNN2MOX-SXaPzWJPOeRTrnLCzYzQZ2e-7HO98AIbj-wEXbrPWSwzIOW2NbNhpWfayHyPYHyJGTRxZmDCHhR_qk79vyb29q1_p-hBCWvY2GsAPu0296IOlq_uQv\/s1600\/langchain.jpg","fifu_image_alt":"","footnotes":""},"categories":[15],"tags":[26,20,24,27],"class_list":["post-228096","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cybersecurity","tag-ai","tag-artificial-intelligence","tag-cybersecurity","tag-vulnerability"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/228096"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=228096"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/228096\/revisions"}],"predecessor-version":[{"id":228098,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/228096\/revisions\/228098"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/228097"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=228096"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=228096"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=228096"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}