CVE Feed

    Dashboard / CVE / CVE-2026-97635

    CVE-2026-97635

    The Agent Zero Web UI before 1.15 does not correctly sanitize user-provided input in chat messages or file uploads. When Agent Zero reproduces content in the chat interface, any injected JavaScript is executed in the context of the victim’s authenticated Agent Zero Web UI session.

    Published:Oct 22, 2026
    Last Modified:Oct 22, 2026
    EPS:Oct 22, 2026
    EPSS Score:
    CVSS Score:8.1

    Affected Products

    Vendor
    Agent-zero
    Product
    Agent-zero

    Exploits

    No exploit reference

    Related CVEs

    CVE-2026-51851 — modelscope agent-zero 1.7, 1.8, 1.9, and 1.10 is vulnerable to Directory Traversal in python/helpers/file_brow…
    CVE-2026-47119 (CVSS 5.3) — Agent Zero before version 1.15 contains a stored cross-site scripting vulnerability that allows attackers to e…
    CVE-2026-47118 (CVSS 7.1) — Agent Zero before version 1.15 contains a path traversal vulnerability that allows unauthenticated attackers t…
    CVE-2026-30624 (CVSS 8.6) — Agent Zero 0.9.8 contains a remote code execution vulnerability in its External MCP Servers configuration feat…
    CVE-2026-4308 (CVSS 2.1) — A weakness has been identified in frdel/agent0ai agent-zero 0.9.7. This affects the function handle_pdf_docume…
    CVE-2026-4307 (CVSS 2.1) — A security flaw has been discovered in frdel/agent0ai agent-zero 0.9.7-10. The impacted element is the functio…
    CVE-2025-55523 (CVSS 3.5) — An issue in the component /api/download_work_dir_file.py of Agent-Zero v0.8.* allows attackers to execute a di…
    CVE-2025-55524 (CVSS 7.3) — Insecure permissions in Agent-Zero v0.8.* allow attackers to arbitrarily reset the system via unspecified vect…
    CVE-2025-6166 (CVSS 5.1) — A vulnerability was found in frdel Agent-Zero up to 0.8.4. It has been rated as problematic. This issue affect…
    CVE-2025-3547 (CVSS 5.3) — A vulnerability classified as critical was found in frdel Agent-Zero 0.8.1.2. This vulnerability affects unkno…

    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