langchain langchain_core CVE Vulnerabilities (4)

CVEs: 4 CPE versions: View versions table

Summary

This page lists publicly disclosed CVE vulnerabilities affecting langchain langchain_core (linked via NVD CPE). Each row includes severity scores, summaries, and publication dates to help identify and analyze security issues.

Showing 14 of 4 CVEs
«« First « Prev Page 1 / 1 Next »
CVE Summary Source Max CVSS EPSS % Published Updated
CVE-2026-40087 LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.84 and 1.2.28, LangChain's f-string prompt-template validation was incomplete in two respects. First, some prompt template classes accepted f-string templates and formatted them without enforcing the same attribute-access validation as PromptTemplate. In particular, DictPromptTemplate and ImagePromptTemplate could accept templates containing attribute access or indexing expressions and subsequently evaluate t [email protected] 5.3 0.26% 2026-04-09 2026-04-16
CVE-2026-34070 LangChain is a framework for building agents and LLM-powered applications. Prior to version 1.2.22, multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension chec [email protected] 7.5 1.07% 2026-03-31 2026-06-01
CVE-2026-26013 LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input. This vulnerability is fixed in 1.2.11. [email protected] 3.7 0.38% 2026-02-10 2026-03-17
CVE-2025-68664 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 r [email protected] 9.3 13.83% 2025-12-23 2026-01-13
«« First « Prev Page 1 / 1 Next »
cvelogic Threat Intelligence