CVE-2026-47391
MervinPraison PraisonAI 취약점
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...
- 대응 우선순위
- 점검
- CVSS
- 9.8
- EPSS
- 0.78% 백분위 52.4% · 2026.08.02 기준
- CISA KEV
- 미등록
- 조치 기한
- -
- 공개일
- 2026.07.22