CVE Feed

    Dashboard / CVE / CVE-2026-55529

    CVE-2026-55529

    PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit tools/call requests to the local MCP server and execute exposed tools. This issue is fixed in version 4.6.58.

    Published:Aug 25, 2026
    Last Modified:Aug 27, 2026
    EPS:Aug 25, 2026
    EPSS Score:0.00124
    CVSS Score:6.9

    Affected Products

    Vendor
    Mervinpraison
    Product
    Praisonai

    Exploits

    No exploit reference

    Common Attack Pattern Enumeration and Classification (CAPEC)

    CAPEC-111 JSON Hijacking (aka JavaScript Hijacking)
    CAPEC-12 Choosing Message Identifier
    CAPEC-141 Cache Poisoning
    CAPEC-142 DNS Cache Poisoning
    CAPEC-160 Exploit Script-Based APIs
    CAPEC-166 Force the System to Reset Values
    CAPEC-21 Exploitation of Trusted Identifiers
    CAPEC-216 Communication Channel Manipulation
    CAPEC-36 Using Unpublished Interfaces or Functionality
    CAPEC-384 Application API Message Manipulation via Man-in-the-Middle
    CAPEC-385 Transaction or Event Tampering via Application API Manipulation
    CAPEC-386 Application API Navigation Remapping
    CAPEC-387 Navigation Remapping To Propagate Malicious Content
    CAPEC-388 Application API Button Hijacking
    CAPEC-510 SaaS User Request Forgery
    CAPEC-59 Session Credential Falsification through Prediction
    CAPEC-60 Reusing Session IDs (aka Session Replay)
    CAPEC-62 Cross Site Request Forgery
    CAPEC-75 Manipulating Writeable Configuration Files
    CAPEC-76 Manipulating Web Input to File System Calls
    CAPEC-89 Pharming

    Related CVEs

    CVE-2026-55536 (CVSS 9.1) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, Browser Server _handle_connection() checks…
    CVE-2026-55532 (CVSS 7.6) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses requ…
    CVE-2026-55533 (CVSS 8.2) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests w…
    CVE-2026-55539 (CVSS 8.6) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, the Jobs API create_app function mounts /a…
    CVE-2026-55527 (CVSS 7.1) — PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the FileMemory constructor joins uns…
    CVE-2026-55541 (CVSS 8.8) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve…
    CVE-2026-55535 (CVSS 6.8) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the Jobs API validate_webhook_url() path f…
    CVE-2026-55537 (CVSS 7.1) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validate_webhook_url() ac…
    CVE-2026-55538 (CVSS 7.3) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, praisonai serve agents parses config["api_…
    CVE-2026-55540 (CVSS 7.1) — PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, is_path_within_directory() uses os.path.ab…

    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