Host code execution via codeMode sandbox escape
Published Sep 15, 2026 · Updated Sep 15, 2026
Code injection in PraisonAI before 1.7.2 allows remote attackers to execute operating-system commands through crafted codeMode input. The codeMode implementation in src/praisonai-ts/src/tools/builtins/code-mode.ts passes the input to new Function inside with(sandbox), while its regular-expression blocklist misses a reconstructed global.require call. Any deployment with codeMode enabled for agents accepts model-influenced code that can read or write process-accessible files and obtain environment credentials with the PraisonAI process privileges.
Summary
What happened
Code injection in PraisonAI before 1.7.2 allows remote attackers to execute operating-system commands through crafted codeMode input. The codeMode implementation in src/praisonai-ts/src/tools/builtins/code-mode.ts passes the input to new Function inside with(sandbox), while its regular-expression blocklist misses a reconstructed global.require call. Any deployment with codeMode enabled for agents accepts model-influenced code that can read or write process-accessible files and obtain environment credentials with the PraisonAI process privileges.
The record
- CVE
- CVE-2026-57141
- Published
- Sep 15, 2026
- Updated
- Sep 15, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-94, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 15, 2026CVE publishedPublication date reported by the CVE source.
- Sep 15, 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=< 1.7.2
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
- GitHub advisory codeMode sandbox-escape 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