CVE-2026-56838

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.

• CWE-78
• CWE-693
• CWE-863

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg

Published

Oct 23, 2026

Last Modified

Oct 29, 2026

Status

Deferred

• Uncovering a hidden BOLA in Appsmith's snapshot logicStrix autonomously discovered a BOLA/IDOR vulnerability in Appsmith's snapshot deletion path.
• Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
• PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
• AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.

• CVE-2026-56832PraisonAI is a multi-agent teams system. From version 4.5.2 …8.8
• CVE-2026-56833PraisonAI is a multi-agent teams system. From version 3.8.1 …7.5
• CVE-2026-56834PraisonAI is a multi-agent teams system. From version 3.8.1 …7.5
• CVE-2026-56835PraisonAI is a multi-agent teams system. From version 3.11.0…8.3
• CVE-2026-56836PraisonAI is a multi-agent teams system. From version 4.5.11…8.2
• CVE-2026-56837PraisonAI is a multi-agent teams system. From version 4.6.56…8.6
• CVE-2026-56839PraisonAI is a multi-agent teams system. Prior to 4.6.59, th…7.3
• CVE-2026-5684A vulnerability was determined in Tenda CX12L 16.03.53.12. A…8
• CVE-2026-56840PraisonAI is a multi-agent teams system. From version 4.5.2 …8.8
• CVE-2026-56841A malicious actor with access to the network and low privile…8.8
• CVE-2026-56842A malicious actor with access to the network and under certa…7.5
• CVE-2026-56843Incorrect authorization in the XML-RPC API of WebPros Plesk …9.9