CVE-2026-47391

Medium

Elevated severity or exploit probability.

CVSS base

9.8 CRITICAL

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS — probability of exploitation (30 days)

1.2%

65.9th percentile

CISA KEV

Not listed

Weakness / dates

CWE-95

Published 2026-07-21 · modified 2026-07-23

CVSS breakdown

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector	N	Network
Attack Complexity	L	Low
Privileges Required	N	None
User Interaction	N	None
Scope	U	Unchanged
Confidentiality	H	High
Integrity	H	High
Availability	H	High

Timeline

2026-07-21 — Published (NVD)
2026-07-23 — Last modified (NVD)

Description

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.

References

Official: NVD · CVE.org