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.
Affected products
praison: praisonaiagents
References1
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6vh… ExploitVendor Advisory
Metrics
- CVSS 3.1
-
10.0
CRITICAL
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H - EPSS — exploit probability
- 13% percentile: 96 · as of 12 November 2026
- CWE
- CWE-693
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.