PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

Summary

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.

Timeline

1. Jul 21, 2026, 3:21 PM UTCCVE published
2. Jul 23, 2026, 2:27 PM UTCCISA SSVC assessment

   Exploitation: poc · Automatable: yes · Technical impact: total

3. Jul 23, 2026, 2:27 PM UTCRecord last updated

Affected versions

• MervinPraison PraisonAI

  fixed in 4.6.40

• praisonaiPyPI

  fixed in 4.6.40

References 3