PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

MITRE NVD CVE.ORG JSON API

Summary

CVECVE-2026-57142
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-10-23 13:17:11 UTC
Updated2026-10-29 14:17:57 UTC
DescriptionPraisonAI 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.

Risk And Classification

Primary CVSS: v3.1 7.8 HIGH from [email protected]

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

EPSS: 0.001460000 probability, percentile 0.038360000 (date 2026-10-29)

Problem Types: CWE-78 | CWE-94 | CWE-863 | CWE-78 CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') | CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection') | CWE-863 CWE-863: Incorrect Authorization

VersionSourceTypeScoreSeverityVector
3.1[email protected]Secondary7.8HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
3.1CNADECLARED7.8HIGHCVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CVSS v3.1 Breakdown

Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA MervinPraison PraisonAI affected >= 4.5.87, < 4.6.61 Not specified

References

ReferenceSourceLinkTags
github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2 134c704f-9b21-4f2e-91b3-4a467353bcc0 github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

© CVE.report 2026

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report