Skip to main content
HIGH

CVE-2026-57137

CVSS v3

8.8

HIGH

EPSS Score

0.5 %

exploit probability, as of 2026-09-28

CISA KEV

No

known exploited

Exploitation

—

SSVC status

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 th

Technical details

Published
2026-09-15
Last Modified
2026-09-15

Frequently asked questions

What is CVE-2026-57137?

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 th

Is CVE-2026-57137 actively exploited?

Active exploitation of CVE-2026-57137 has not been confirmed. Its EPSS score was 0.5% on 2026-09-28, the estimated probability of exploitation in the next 30 days.

What is the CVSS score for CVE-2026-57137?

CVE-2026-57137 has a CVSS v3 base score of 8.8 (HIGH severity).

Is CVE-2026-57137 affecting your environment?

Use isMalicious to check if any of your IPs or domains are associated with this vulnerability's IOCs.

No credit card required · 500 free checks/month · Free API key