CVE-2026-34938
CriticalCVSS 10.0Exploitation Probability (EPSS)
Elevated risk67th percentile - higher than 67% of all known CVEs
Summary
PraisonAI prior to version 1.5.90 has a vulnerability in execute_code() that allows bypassing a three-layer sandbox by passing a str subclass with an overridden startswith() method, leading to arbitrary OS command execution.
Risk Assessment
An authenticated attacker can gain full control of the server hosting PraisonAI.
Recommendation
Upgrade PraisonAI to version 1.5.90 or later.
Original NVD description (English source)
PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.