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.
Analysis
No analysis available yet.
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| MervinPraison | PraisonAI | affected |
|
No data.
No data.
No data available yet.
Remediation
No remediation available yet.
Tracking
Sign in to view the affected projects.
Advisories
| Source | ID | Title |
|---|---|---|
 Github GHSA |
GHSA-vg22-4gmj-prxw | PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution |
References
History
Tue, 21 Jul 2026 16:00:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| 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. | |
| Title | PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution | |
| Weaknesses | CWE-306 CWE-95 |
|
| References |
| |
| Metrics |
cvssV3_1
|
Subscriptions
No data.
MITRE
Status: PUBLISHED
Assigner: GitHub_M
Published:
Updated: 2026-07-21T15:21:22.916Z
Reserved: 2026-05-19T19:22:45.729Z
Link: CVE-2026-47391
Vulnrichment
No data.
NVD
No data.
Redhat
No data.
OpenCVE Enrichment
No data.