CVE Feed

    Dashboard / CVE / CVE-2025-55733

    CVE-2025-55733

    DeepChat is a smart assistant that connects powerful AI to your personal world. DeepChat before 0.3.1 has a one-click remote code execution vulnerability. An attacker can exploit this vulnerability by embedding a specially crafted deepchat: URL on any website, including a malicious one they control. When a victim visits such a site or clicks on the link, the browser triggers the app’s custom URL handler (deepchat:), causing the DeepChat application to launch and process the URL, leading to remote code execution on the victim’s machine. This vulnerability is fixed in 0.3.1.

    Published:Aug 19, 2025
    Last Modified:Sep 17, 2025
    EPS:Aug 19, 2025
    EPSS Score:0.00147
    CVSS Score:9.7

    Affected Products

    Vendor
    Thinkinai
    Product
    Deepchat

    Exploits

    https://github.com/ThinkInAIXYZ/deepchat/security/advisories/GHSA-hqr4-4gfc-5p2jhttps://github.com/ThinkInAIXYZ/deepchat/security/advisories/GHSA-hqr4-4gfc-5p2j

    Related CVEs

    CVE-2026-43899 (CVSS 9.6) — DeepChat is an open-source artificial intelligence agent platform that unifies models, tools, and agents. Prio…
    CVE-2026-43900 (CVSS 9.3) — DeepChat is an open-source artificial intelligence agent platform that unifies models, tools, and agents. Prio…
    CVE-2025-67744 (CVSS 9.6) — DeepChat is an open-source artificial intelligence agent platform that unifies models, tools, and agents. Prio…
    CVE-2025-66481 (CVSS 9.6) — DeepChat is an open-source AI chat platform that supports cloud models and LLMs. Versions 0.5.1 and below are …
    CVE-2025-66222 (CVSS 9.6) — DeepChat is a smart assistant uses artificial intelligence. In 0.5.0 and earlier, there is a Stored Cross-Site…
    CVE-2025-58768 (CVSS 9.6) — DeepChat is a smart assistant uses artificial intelligence. Prior to version 0.3.5, in the Mermaid chart rende…

    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