CVE-2026-47391
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()`.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (1.17%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 3.1
- 9.8 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 1.17% probability · 65th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-95, CWE-306
- Source
- security-advisories@github.com
References
- https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747
- https://github.com/MervinPraison/PraisonAI/pull/1793
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.