CVE-2026-39888
PraisonAIAgents has a sandbox escape via exception frame traversal in `execute_code` (subprocess mode)
In short
PraisonAI's code sandbox can be escaped by exploiting exception frames to access hidden Python functions. An attacker can run unrestricted code despite the security restrictions meant to block dangerous operations.
Technical detail
The execute_code() function uses incomplete attribute blocking (11 vs 30+ names) in subprocess sandbox mode, omitting __traceback__, tb_frame, f_back, and f_builtins. An attacker can chain these exception frame attributes to access the wrapper's real __builtins__ dict and retrieve exec() under an unblocked name, fully bypassing sandbox restrictions. No authentication required; vulnerability requires only ability to provide input to execute_code().
Summary generated and translated by AI from the official description.
PraisonAI is a multi-agent teams system. Prior to 1.5.115, execute_code() in praisonaiagents.tools.python_tools defaults to sandbox_mode="sandbox", which runs user code in a subprocess wrapped with a restricted __builtins__ dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess wrapper (blocked_attrs of python_tools.py) contains only 11 attribute names — a strict subset of the 30+ names blocked in the direct-execution path. The four attributes that form a frame-traversal chain out of the sandbox are all absent from the subprocess list (__traceback__, tb_frame, f_back, and f_builtins). Chaining these attributes through a caught exception exposes the real Python builtins dict of the subprocess wrapper frame, from which exec can be retrieved and called under a non-blocked variable name — bypassing every remaining security layer. This vulnerability is fixed in 1.5.115.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Affected products
MervinPraison · praisonaiagentsWant to know if your infrastructure is exposed to this?
Talk to TrueHacking →