{"id":"CVE-2026-56838","published":"2026-10-23T12:18:15.357","lastModified":"2026-10-23T12:18:15.473","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.","cvssScore":7.8,"cvssSeverity":"HIGH","cvssVector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","cwes":["CWE-78","CWE-693","CWE-863"],"vendors":[],"products":[],"references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg","tags":[]}],"exploitRefs":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg","tags":[]}],"hasPoc":true,"ai":null}