CVE-2026-57142
PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml
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.
INFO
Published Date :
Oct. 23, 2026, 1:17 p.m.
Last Modified :
Oct. 23, 2026, 1:17 p.m.
Remotely Exploit :
No
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | HIGH | github | ||||
| CVSS 3.1 | HIGH | MITRE-CVE | ||||
| CVSS 3.1 | HIGH | [email protected] |
Solution
- Parse workflow tools before checking recipe policy.
- Include workflow tools in dangerous-tool policy checks.
- Treat 'approve:' as operator policy, not bypass.
- Add regression tests for tool policy enforcement.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-57142.
| URL | Resource |
|---|---|
| https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2 |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-57142 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-57142
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-57142 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-57142 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
New CVE Received by [email protected]
Oct. 23, 2026
Action Type Old Value New Value Added 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. Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-94 Added CWE CWE-78 Added CWE CWE-863 Added Affected New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/57xxx/CVE-2026-57142.json">CVE-2026-57142</a> Added Reference https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2