Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-57123 – Unauthenticated Remote Code Execution via MCP SSE Transport – PraisonAI praisonaiag

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-57123 is a critical missing-authentication vulnerability in PraisonAI’s praisonaiagents package, affecting the Model Context Protocol (MCP) Server-Sent Events (SSE) transport. The SSE server binds to 0.0.0.0 and exposes /sse and /messages/ routes without enforcing any of the authentication, Origin-validation, or DNS-rebinding protections otherwise available in the framework’s SecurityConfig. Any network-reachable client — or a malicious website via DNS rebinding against a locally-bound instance — can list and invoke all registered MCP tools, resulting in a CVSS v3.1 score of 9.8 (Critical).

Technical details

  • Root cause: The ToolsMCPServer.run_sse and launch_tools_mcp_server functions create the /sse and /messages/ HTTP routes but never invoke the framework’s existing SecurityConfig checks for authentication, Origin header validation, or DNS-rebinding protection.
  • Trigger conditions: An application must expose an MCP tool server over SSE transport (the default binds to 0.0.0.0, making it reachable from any network path that can route to the host, not just localhost).
  • Attack vector: Network (AV:N), no privileges or user interaction required. A remote attacker can connect directly to the exposed SSE endpoint, or lure a victim’s browser to a malicious page that performs DNS rebinding to reach an instance otherwise assumed to be bound to localhost.
  • Impact: Full enumeration and invocation of all tools registered on the MCP server, which can lead to arbitrary code execution, data exfiltration, or further compromise depending on what tools/capabilities are registered — resulting in high impact to confidentiality, integrity, and availability.

Affected software

  • Product: praisonaiagents (PraisonAI)
  • Vendor: MervinPraison
  • Vulnerable versions: prior to 1.6.59
  • Fixed version: 1.6.59 (corresponding release tagged v4.6.59)

Severity

  • CVSS v3.1 Base Score: 9.8 (Critical)
  • Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Mitigation and recommended actions

  • Immediate: Upgrade praisonaiagents to version 1.6.59 or later, which applies SecurityConfig enforcement (authentication, Origin validation, and DNS-rebinding protection) to the MCP SSE transport routes.
  • If immediate patching is not possible:
    • Do not expose MCP SSE endpoints (/sse, /messages/) on 0.0.0.0 or to untrusted networks; restrict listening interfaces to localhost only where feasible.
    • Place the MCP server behind a reverse proxy or firewall that enforces authentication and validates the Origin header before allowing connections.
    • Block inbound access to the SSE/MCP ports from the public internet and untrusted internal segments until patched.
    • Audit which tools are registered on any exposed MCP server instances, since any of them could be invoked by an unauthenticated attacker.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge