CVE-2026-61447 PUBLISHED

PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

Assigner: VulnCheck
Reserved: 09.07.2026 Published: 11.07.2026 Updated: 11.07.2026

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Metrics

CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
CVSS Score: 10

Product Status

Vendor MervinPraison
Product PraisonAI
Versions Default: unaffected
  • affected from 0 to 1.6.78 (excl.)
  • Version 1.6.78 is unaffected

Credits

  • anushkavirgaonkar reporter

References

Problem Types

  • Improper Control of Generation of Code ('Code Injection') CWE