PHP2Shell : See if you’re affected with a free external attack surface scan. Click Here > 

Back
New CVE Detected

CVE-2026-57134 – Authentication Bypass – PraisonAI (npm) MCPSecurity 1.5.1–1.7.1

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

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-57134 is an authentication bypass vulnerability (CWE-287/CWE-288/CWE-863) in the MCPSecurity authentication helper of the npm praisonai package, part of the PraisonAI multi-agent framework. The library’s policy evaluator fails to validate credentials for the "basic" and "oauth" authentication methods it advertises, allowing an attacker to bypass authentication controls on MCP (Model Context Protocol) servers that rely on this component. The issue is rated High severity (CVSS 8.2) and is remotely exploitable with no privileges or user interaction required.

Technical details

  • Root cause: The MCPSecurity.evaluatePolicy() function (in src/praisonai-ts/src/mcp/security.ts) only invokes the developer-supplied credential validation callback when the configured authentication method is api-key or bearer. The basic and oauth branches never call the validator, so any non-empty Authorization header is treated as authenticated regardless of whether the credentials are valid.
  • Trigger conditions: A developer must configure an MCP server or tool to use MCPSecurity with a basic or oauth authentication policy (expecting a custom validation callback to be enforced).
  • Attack vector: Network — an unauthenticated remote attacker simply sends a request with any non-empty Authorization header (no valid credentials required) to a service protected by the affected basic/oauth policy.
  • Impact: Authentication bypass allowing access to protected MCP tools and resources, execution of authenticated tool calls, reading of protected data, triggering of workflow actions, and circumvention of audit/authorization controls. The CVSS vector (C:H/I:L/A:N) reflects a high confidentiality impact with limited integrity impact and no availability impact.

Affected software

  • Vendor/Project: MervinPraison / PraisonAI
  • Package: praisonai (npm package, TypeScript implementation)
  • Vulnerable versions: 1.5.1 through 1.7.1 (inclusive)
  • Fixed version: 1.7.2

Severity

  • CVSS v3.1 Base Score: 8.2 (High)
  • Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Mitigation and recommended actions

  • Immediate: Upgrade the praisonai npm package to version 1.7.2 or later, where the validation callback is correctly invoked for all advertised authentication methods.
  • If immediate patching is not possible:
    • Avoid relying on basic or oauth authentication policies within MCPSecurity until patched; use api-key or bearer methods, which correctly enforce the validation callback, or implement independent authentication/authorization checks in front of the MCP server.
    • Restrict network exposure of MCP servers using this library to trusted networks or place them behind a properly validating reverse proxy/API gateway until the upgrade is applied.
    • Audit logs for MCP tool calls and resource access made via basic/oauth-configured endpoints for signs of unauthorized access predating the patch.

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