VYPR
High severity8.8NVD Advisory· Published Sep 15, 2026· Updated Sep 15, 2026

CVE-2026-57137

CVE-2026-57137

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
praisonainpm
>= 1.4.0, < 1.7.21.7.2

Affected products

1

Patches

Vulnerability mechanics

References

4

News mentions

0

No linked articles in our index yet.