7.8High

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

MervinPraison PraisonAI Published: (27 days ago)

Description

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.

Weakness (CWE): CWE-78CWE-693CWE-863

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
MervinPraison PraisonAI >= 4.5.87, < 4.6.59

References and patches