Sign in Sign up
JA · EN · FR
SecPulse
Categories
CVE-2026-47391 critical CVSS 9.8

Vulnerability in PraisonAI (CVE-2026-47391)

Summary

Vulnerability in PraisonAI (CVE-2026-47391). Successful exploitation can lead to full system takeover. Exploitable via POST /a2a. Mitigation: upgrade to 4.6.40 or later.

Original description

The description as published by the source.

Summary

The first-party PraisonAI A2A server example combines three behaviors into a remotely exploitable Critical chain:

  1. The example exposes an A2A server without configuring auth_token.
  2. The same example binds the server to 0.0.0.0.
  3. The example registers a calculate(expression) tool implemented with Python eval(expression).

An unauthenticated network client can send a JSON-RPC message/send request to /a2a. The A2A handler passes the attacker-controlled message to agent.chat(). With a real Gemini LLM (gemini/gemini-2.5-flash-lite), the model invoked the registered calculate tool, causing the example's eval() call to execute Python in the server process. The canary wrote a marker file from an unauthenticated /a2a request.

This is not a claim that every A2A deployment is automatically RCE. The Critical chain is confirmed for the first-party A2A example, and for deployments that follow the same pattern: public unauthenticated A2A plus an unsafe tool such as this eval()-based calculate tool. The default unauthenticated A2A surface is the remote entry point; the official example's eval() tool provides the code execution sink.

Earlier note:

The unsafe official example existed earlier, but the complete unauthenticated /a2a message/send to agent.chat() exploit chain is only claimed here for versions where that endpoint is present and confirmed.

Trust Boundary

The boundary that should be preserved is:

Unauthenticated ne…

Source: GitHub Security Advisories (Global) NVD GitHub Advisory

Auto-generated summary

Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.

A vulnerability tracked as CVE-2026-47391 has been found in PraisonAI.
Attackers can target a specific entry point like POST /a2a over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 9.8/10.
What to do: upgrade PraisonAI to 4.6.40 or later.
If unsure, ask your IT team or search "PraisonAI CVE-2026-47391" on the vendor's site.

CVE-2026-47391 (PraisonAI) — CWE-306 / CVSS v3 9.8
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /a2a / auth_token / calculate / DataPart
Patched: 4.6.40 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.

❓ What is the problem

A vulnerability (CWE-306) exists in PraisonAI. Attackers reach the vulnerable code path via POST /a2a without authentication.

📍 Affected scope

Check the vendor advisory for the affected versions of PraisonAI. Attack surface: POST /a2a / auth_token / calculate / DataPart.

🔥 Severity

Severity: Critical (CVSS 9.8/10). Successful exploitation can lead to full system takeover.

🔧 How to fix

Update to 4.6.40.

🛡️ Workaround

Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.

🔍 Detection

Search webserver/proxy logs for unusual POST /a2a requests with malformed payloads or SQL meta-characters. Run grep -r 'PraisonAI' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response actions

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify 
    grep -r 'PraisonAI' . | grep -v node_modules

    リポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で PraisonAI を grep し、稼働しているサービス・バージョンを把握する。

  2. 2
    Hunt for indicators of compromise detect 
    grep 'POST /a2a' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'

    アクセスログで POST /a2a への異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。

  3. 3
    Apply patch patch 
    Upgrade PraisonAI to 4.6.40

    ステージング環境で 4.6.40 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 2 で見つけた異常検知の続報チェックを含めること。

  4. 4
    Post-deployment verification verify 
    Replay attack against POST /a2a on staging to confirm patch closes the vector

    パッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 2 と同じログクエリでアラート再発が無いか継続監視。

Affected packages

pip PraisonAI
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"4.6.40"}]}]
PyPI praisonai
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"4.6.40"}]}]

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details