CVE-2026-57142 Details
Description
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.
A vulnerability exists in PraisonAI versions 4.5.87 prior to 4.6.61, allowing untrusted recipes to bypass the dangerous-tool policy. This policy is designed to block default-denied tools unless explicitly allowed by the caller. The issue arises because the policy only considers tools declared in 'TEMPLATE.yaml' requires.tools'. In steps-based recipes, the 'workflow.yaml' can be manipulated to self-approve dangerous tools, such as 'execute_command', which is a default-denied tool with critical risk. If an operator runs an untrusted recipe or exposes the recipe runner to users who can choose recipe names or URIs, this vulnerability can be exploited, potentially leading to unauthorized execution of critical shell commands with the privileges of the PraisonAI process.
Users should update to PraisonAI version 4.6.61 or later, where this vulnerability has been patched.
Metrics
CVSS 4.0 Severity and Vector Strings:
VolerionCVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Oct 23, 2026CISA-ADP
Assessed Oct 29, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2 | CISA-ADP | AdvisoryExploitRemedyVendor |
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2 | [email protected] | AdvisoryExploitRemedyVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-78 | Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') | [email protected] |
| CWE-863 | Incorrect Authorization | [email protected] |
| CWE-94 | Improper Control of Generation of Code ('Code Injection') | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| MervinPraison PraisonAI | >= 4.5.87, <= 4.6.57 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Oct 29, 2026 | CVE Modified | CISA-ADP |
| Oct 23, 2026 | New CVE Received | [email protected] |