CVE-2026-57137

Summary

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 Software

VendorProductVersion RangeStatus
MervinPraisonPraisonAI>= 1.4.0, < 1.7.2affected

Weaknesses

  • CWE-693: CWE-693: Protection Mechanism Failure
  • CWE-862: CWE-862: Missing Authorization
  • CWE-863: CWE-863: Incorrect Authorization

ADP Enrichment

CISA ADP Vulnrichment

  • SSVC:
  • Exploitation: poc
    • Automatable: no
    • Technical Impact: total

Additional References

References