# CVE-2026-57137

## Summary

- **CVE ID:** CVE-2026-57137
- **Severity:** HIGH
- **CVSS Score:** 8.8 (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H)
- **CWE:** CWE-693, CWE-862, CWE-863
- **Published:** Sep 15, 2026
- **Last Modified:** Sep 15, 2026

## Description

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.

## Affected Products

- MervinPraison — PraisonAI (>= 1.4.0, < 1.7.2)

## References

- [CNA](https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4)
- [CNA](https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9)
- [CNA](https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.36%
- **EPSS Percentile:** 29.7

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-18._