CVE-2026-56838: PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

Published Oct 23, 2026
·
Updated

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 allowdangeroustools=True. The normal recipe.run() path enforces this with checktoolpolicy(). The streaming path, recipe.runstream(), loads the same recipe, checks dependencies, and then calls executerecipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares executecommand in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.runstream() with allowdangeroustools=False. This issue has been patched in version 4.6.59.

Affected Software

1 affected component
pypi/praisonai>=4.5.87<4.6.59

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade PraisonAI to a version that resolves this vulnerability.

    Fixed in 4.6.59

Event History

Oct 23, 2026
CVE Published
via MITRE·11:58 AM
Data Sourced
via MITRE·11:58 AM
DescriptionSeverityWeakness

Frequently Asked Questions

1

Which deployments are affected?

PraisonAI versions 4.5.87 through versions before 4.6.59 are affected when recipes are executed through recipe.run_stream(). Version 4.6.59 contains the patch.

2

What must an attacker be able to do to exploit this?

Exploitation requires use of the recipe.run_stream() execution path with a recipe that declares a dangerous tool such as execute_command in TEMPLATE.yaml requires.tools. User interaction is required according to the supplied severity vector.

3

Are default dangerous-tool restrictions effective for streaming recipes?

No. In affected versions, recipe.run_stream() can reach the execution engine without the dangerous-tool policy check, even when allow_dangerous_tools=False. The equivalent recipe.run() path performs _check_tool_policy() and denies default-blocked dangerous tools.

4

What can be done before upgrading?

Avoid using recipe.run_stream() for recipes that may declare or invoke dangerous tools, particularly execute_command. Use recipe.run(), which enforces the dangerous-tool policy check, until upgrading to version 4.6.59.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203