p PatchFirst

CVE-2026-57137

CVE-2026-57137 · PraisonAI AgentLoop onToolCall approval runs after tool execution

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 8.8 · High · EPSS 0.5% · Fix available

Published
Updated

Stack: node

Affected products and versions

  • praisonai

    Versions
    • >= 1.4.0, < 1.7.2: Affected

    No fix published

  • praisonai npm

    Affected ranges
    • SEMVER: ≥ 1.4.0, < 1.7.2

    Update to 1.7.2

Original sources

Check your server →