CVEvulnerability

CVE-2026-56838

7.8 HIGH Published 2026-10-23 Modified 2026-10-29 Official page ↗
Status
Deferred
Published
2026-10-23
Last modified
2026-10-29
Assigner
[email protected]
CVSS 3.1 ([email protected])
7.8 HIGH — CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Weaknesses
CWE-693, CWE-78, CWE-863

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.

Related

Weakness · CWE (3)

  • CWE-693 Protection Mechanism Failure weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command weakness
  • CWE-863 Incorrect Authorization weakness

References