Vulnerability Description
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.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Praison | Praisonaiagents | < 1.5.90 |
Related Weaknesses (CWE)
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6vh2-h83c-92ExploitVendor Advisory
FAQ
What is CVE-2026-34938?
CVE-2026-34938 is a vulnerability with a CVSS score of 10.0 (CRITICAL). 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 ...
How severe is CVE-2026-34938?
CVE-2026-34938 has been rated CRITICAL with a CVSS base score of 10.0/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-34938?
Check the references section above for vendor advisories and patch information. Affected products include: Praison Praisonaiagents.