Vulnerability · Published Apr 8, 2026 · Assigned by GitHub_M
CVE-2026-39888PraisonAIAgents has a sandbox escape via exception frame traversal in `execute_code` (subprocess mode)
Critical 10.0
In plain English
A critical-severity security flaw in praisonaiagents from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 43% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonaiagents | 1.5.115 | GHSA-qf73-2hrx-xprp |
| PyPI | praisonaiagents | 1.5.115 | PYSEC-2026-486 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | praisonaiagents | < 1.5.115 |
Weakness: CWE-657, CWE-693 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H