Host command execution via print builtins leak
Published Jul 21, 2026 · Updated Jul 21, 2026
Sandbox escape in PraisonAI before 4.6.40 allows remote authenticated users to execute arbitrary OS commands through crafted agent input. The execute_code() path in praisonaiagents/tools/python_tools.py accepts print.self, exposing builtins; vars() and a runtime-built import key then evade its AST denylist. Any party able to influence agent input through direct code, prompt injection, or a malicious document can act with the PraisonAI process's host permissions.
Summary
What happened
Sandbox escape in PraisonAI before 4.6.40 allows remote authenticated users to execute arbitrary OS commands through crafted agent input. The execute_code() path in praisonaiagents/tools/python_tools.py accepts print.self, exposing builtins; vars() and a runtime-built import key then evade its AST denylist. Any party able to influence agent input through direct code, prompt injection, or a malicious document can act with the PraisonAI process's host permissions.
The record
- CVE
- CVE-2026-47392
- Published
- Jul 21, 2026
- Updated
- Jul 21, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-693, CWE-184, T1059.006
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 21, 2026CVE publishedPublication date reported by the CVE source.
- Jul 21, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 4.6.40
- Affected versionversion=praisonaiagents
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- execute_code print.__self__ sandbox bypass proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo