CVE-2026-57134: PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation
PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured credential validator only when AuthMethod is api-key or bearer. Basic and OAuth policies accept any non-empty Authorization header without calling auth.validate(), then return an authenticated result, allowing callers with invalid credentials to access MCP tools and resources protected by those policies. This issue is fixed in version 1.7.2.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade to a fixed release to a version that resolves this vulnerability.
Fixed in 1.7.2
Event History
Frequently Asked Questions
Which deployments are exposed to this issue?
PraisonAI versions from 1.5.1 through 1.7.2 are affected when MCP tools or resources are protected using MCPSecurity Basic or OAuth authentication policies. API-key and bearer authentication policies invoke the configured credential validator and are not described as affected.
What does an attacker need to exploit the vulnerability?
An unauthenticated remote caller only needs to send a non-empty Authorization header to an endpoint protected by a Basic or OAuth policy. The supplied credentials do not need to be valid because the validator is not called.
What access could an attacker gain?
The caller can receive an authenticated result and access MCP tools and resources protected by the affected Basic or OAuth policies. The stated impact includes high confidentiality impact and low integrity impact.
What should be done if upgrading is not immediately possible?
The provided information identifies version 1.7.2 as the fix. Until it can be applied, avoid relying on MCPSecurity Basic or OAuth policies to protect MCP tools and resources, or restrict access to those services through controls outside the affected policy evaluation.