Skip to main content
Public proof of conceptFix available

CVE-2026-47391

A public proof of concept exists; no exploitation attested.

  • Published2026-07-21
  • Fixed in4.6.40
  • WeaknessCWE-306 · CWE-95

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

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.

Timeline

dates in UTC
  1. 2026-07-2116:17CVE publishedNVD

Versions per branch

OSV
praisonai
BranchAffectedFixed in
4.6< 4.6.404.6.40

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Products declared by the CNA1 product

As GitHub_M, the CNA that assigned this CVE, declared them in the CVE record; versions as written.

  • MervinPraison PraisonAI
    Affected
    • = < 4.6.40no fix stated

Source: the CNA record (CVE Program), © The MITRE Corporation,CVE Terms of UseCVE recordupdated 2026-07-21

Fix

  1. Update praisonai to 4.6.40

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof of concept
Metasploit modules
none listed
Metasploit Framework

Sources

  • NVDCVE recordread 2026-10-25
  • CISA-ADPSSVC decisionpoc2026-07-23
  • CNACVSS 3.19.8known since 2026-10-25
  • CNAweakness (CWE)CWE-306, CWE-95known since 2026-10-25
  • FIRST EPSSEPSS score1.5 %2026-11-08
  • OSVaffected packages—
  • GitHub AdvisoriesadvisoryCRITICAL2026-05-29

Identifiers

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Published
2026-07-21
Last Modified
2026-10-24
NVD status
Deferred
GitHub Advisory
GHSA-vg22-4gmj-prxw

Frequently asked questions

What is CVE-2026-47391?

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.

Is CVE-2026-47391 actively exploited?

A proof-of-concept exploit exists for CVE-2026-47391, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2026-47391?

CVE-2026-47391 has a CVSS v3 base score of 9.8 (CRITICAL severity), with vector string CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.

Running praisonai? Hear about its next vulnerability

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

Get alerts for this productCISA KEV additions, November 2026Search CVEs

No credit card required · No monthly cap on website lookups · 250 API requests/month

Go further

Related vulnerabilities

Same product first, then the same vendor advisory and the same publication week.

Back to CVE Database

Sources for this record