Sandboxed attribute disclosure via format field traversal
Published Sep 14, 2026 · Updated Sep 14, 2026
Protection mechanism failure in PraisonAI praisonaiagents before 1.6.59 allows remote authenticated users to read sandboxed object attributes. Runtime-built dunder names evade AST checks, while str.format and str.format_map resolve dotted fields through C-level access that bypasses _safe_getattr. The read primitive requires prompt-influenced code to reach execute_code with approval automatically granted; no complete execution chain is established.
Summary
What happened
Protection mechanism failure in PraisonAI praisonaiagents before 1.6.59 allows remote authenticated users to read sandboxed object attributes. Runtime-built dunder names evade AST checks, while str.format and str.format_map resolve dotted fields through C-level access that bypasses _safe_getattr. The read primitive requires prompt-influenced code to reach execute_code with approval automatically granted; no complete execution chain is established.
The record
- CVE
- CVE-2026-57120
- Published
- Sep 14, 2026
- Updated
- Sep 14, 2026
- Vendor
- PraisonAI
- Product
- praisonaiagents
- Classifications
- CWE-693
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Sep 14, 2026CVE publishedPublication date reported by the CVE source.
- Sep 14, 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=< 1.6.59
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 format-field sandbox bypass reproducerproof 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