CVE-2026-57142

What it is

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61.

At a glance

Exploitability

Can be exploited locally on the machine without logging in, but needs a user to act. High risk of data exposure, data tampering, service disruption.

Exploit odds

0.2% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-10-23 13:17 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-29 14:17 UTC Last updatedMost recent change to the record

Details

Published

2026-10-23 13:17 UTC

Last modified

2026-10-29 14:17 UTC

Exploit probability

0.2% · EPSS, next 30 days

Weakness

CWE-78 · OS command injection

Record status

Deferred

Attack profile CVSS 3.1 · 7.8

Attack vector

Local

Complexity

Low

Privileges needed

None

User interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High