CVE Watchtower


← Back to CVE List

CVE-2026-47391NVD

Vulnerability 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.
Severity Level
CRITICAL(9.8)
Published Date
Jul 21, 2026
Last Modified
Jul 21, 2026
Exploitation Status
No confirmed exploitation yet
EPSS Score (30-Day)
0.08%Probability
Root Weakness (CWE)
Refer to the official MITRE database for detailed architectural specifications regarding this weakness.
CVSS v3.1 Base Metrics
Attack VectorNetwork
Attack ComplexityLow
Privileges RequiredNone
User InteractionNone
ScopeUnchanged
ConfidentialityHigh
IntegrityHigh
AvailabilityHigh