PraisonAI: Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety Controls
CVE-2026-40149 · GHSA-4wr3-f4p3-5wjh · published 2026-04-10
- Severity
- High
- CVSS score
- 7.9
- Chance of exploitation (EPSS)
- 0.24%
- Fixed in
- 4.5.128
- Exploitation Public proof of concept
- Automatable No
- Technical impact Partial
- CISA SSVC
Bypasses human-in-the-loop safety controls: The approval system is the primary safety mechanism preventing agents from executing dangerous operations (shell commands, file writes, code execution) without human review. Once the allowlist is manipulated, all safety gates for the specified tools are permanently disabled for the lifetime of the gateway process. Enables arbitrary agent tool execution: Any tool can be added to the allowlist, including tools that execute shell commands, write files, or perform other privileged operations. Persistent within process: The allowlist is stored in-memory and persists for the entire gateway lifetime. There is no audit log of allowlist modifications.
Upgrade praisonai to 4.5.128 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
The approval allowlist endpoint is a security-critical function and should always require authentication, even in development mode. Apply one of these mitigations: Option A: Require authtoken for approval endpoints (recommended)**
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| praisonai | PyPI | < 4.5.128 | 4.5.128 |
1 registered MCP server installs an affected version today, by the dependency versions a fresh install resolves.
- io.github.MervinPraison/praisonaipraisonai@2.3.42
- CriticalMarimo: Pre-Auth Remote Code Execution via Terminal WebSocket Authentication BypassmarimoExploited
- CriticalLangflow CORS misconfiguration enables Account Takeover and RCElangflowExploited
- HighLiteLLM: MCP Authentication Bypass via OAuth2 Passthrough FallbacklitellmExploited
- HighLangflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's FlowlangflowExploited
- CriticalTodoist MCP Server: Browser DNS rebinding lets websites write and delete Todoist data through local MCP server@doist/todoist-mcp
- CriticalLangflow: Unauthenticated Flow Execution via Webhook Authentication Bypasslangflow
- CriticalPraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Callspraisonai
- CriticalPraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generationpraisonai
- CriticalPraisonAI has a Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92praisonai
- CriticalPraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validationpraisonai
- CriticalPraisonAI: Unauthenticated RCE via Jobs API + Approval Bypasspraisonaiagents, praisonai
- CriticalPraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocationpraisonai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.