Skip to content
Fencer Intel
critical 9.8

CVE-2026-47391 json

PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

published 5mo ago modified 18d ago also EUVD-2026-46281 , GHSA-vg22-4gmj-prxw , PYSEC-2026-478

cvss
9.8
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
1.5%
EPSS 1.5% chance of exploitation in 30 days, percentile 74%
public exploits
0
none known

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.

Patch / fix

  • pypi praisonai 4.6.40
  • praison praisonai 4.6.40

Is CVE-2026-47391 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
total
Assessed
3mo ago

Exploit prediction

1.50% chance of exploitation in the next 30 days, higher than 74% of all scored CVEs (FIRST EPSS, 2026-11-11).

Exploits and checks

  • github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
OSV 3.1 9.8 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem package affected fixed in
pypi praisonai
<4.6.40
4.6.40

Affected products

  • MervinPraison PraisonAI

Classification

Weakness
  • CWE-95 Improper Neutralization of Directives in Dynamically Evaluated Code
  • CWE-306 Missing Authentication for Critical Functionality

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.