CVE Feed

    Dashboard / CVE / CVE-2024-5998

    CVE-2024-5998

    A vulnerability in the FAISS.deserialize_from_bytes function of langchain-ai/langchain allows for pickle deserialization of untrusted data. This can lead to the execution of arbitrary commands via the os.system function. The issue affects the latest version of the product.

    Published:Sep 17, 2024
    Last Modified:Jul 30, 2025
    EPS:Sep 17, 2024
    EPSS Score:0.00129
    CVSS Score:7.8

    Affected Products

    Vendor
    Langchain
    Product
    Langchain

    Exploits

    https://huntr.com/bounties/fa3a2753-57c3-4e08-a176-d7a3ffda28fe

    Common Attack Pattern Enumeration and Classification (CAPEC)

    CAPEC-586 Object Injection

    Related CVEs

    CVE-2026-44843 (CVSS 8.2) — LangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChai…
    CVE-2026-30617 (CVSS 8.6) — LangChain-ChatChat 0.3.1 contains a remote code execution vulnerability in its MCP STDIO server configuration …
    CVE-2024-58340 (CVSS 8.7) — LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service (ReDoS) vulnerabil…
    CVE-2025-67644 (CVSS 7.3) — LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync a…
    CVE-2025-64439 (CVSS 7.4) — LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync a…
    CVE-2025-64104 (CVSS 7.3) — LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync a…
    CVE-2025-8709 (CVSS 7.3) — A SQL injection vulnerability exists in the langchain-ai/langchain repository, specifically in the LangGraph's…
    CVE-2025-9556 (CVSS 9.8) — Langchaingo supports the use of jinja2 syntax when parsing prompts, which is in turn parsed using the gonja li…
    CVE-2025-45150 (CVSS 9.8) — Insecure permissions in LangChain-ChatGLM-Webui commit ef829 allows attackers to arbitrarily view and download…
    CVE-2025-46059 (CVSS 9.8) — langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit …

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High