---
id: CVE-2026-56838
title: PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
summary: >-
  PraisonAI is a multi-agent teams system. From version 4.5.87 to before version
  4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools
  unless the caller explicitly passes allow_dangerous_tools=True. The normal
  recipe.run…
severity: high
cvss: 7.8
cvssVector: 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'
cvssSource: cna
cwe:
  - CWE-78
  - CWE-693
  - CWE-863
vendor: MervinPraison
product: PraisonAI
affected:
  - 'PraisonAI >= 4.5.87, < 4.6.59'
ssvc:
  exploitation: poc
  automatable: 'no'
  technicalImpact: total
  timestamp: '2026-10-29T13:52:31.231130Z'
exploitAvailable: true
published: '2026-10-23'
updated: '2026-10-29'
sourceUpdated: '2026-10-29T13:53:23.978Z'
source: CVEORG
sourceUrl: 'https://www.cve.org/CVERecord?id=CVE-2026-56838'
references:
  - url: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg
    label: >-
      https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg
  - url: 'https://github.com/MervinPraison/PraisonAI'
tags:
  - cve.org
  - exploit-available
  - osv
  - pip
epss: 0.00146
epssPercentile: 0.03841
aliases:
  - GHSA-v847-hxxw-3pxg
ecosystem: pip
patched:
  - praisonai 4.6.59
ingestedAt: '2026-07-21T19:04:57.649Z'
---

## Overview

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.

## Affected

- `PraisonAI >= 4.5.87, < 4.6.59`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

## Package advisory (CVE-2026-56838)

Affected packages:

- `praisonai >= 4.5.87, < 4.6.59`

Patched in:

- `praisonai 4.6.59`

Source: https://osv.dev/vulnerability/GHSA-v847-hxxw-3pxg