CyberRota Analysis
AI-GeneratedThe vulnerability in PraisonAI allows for the execution of blocklisted dunder names in sandbox mode, enabling unauthorized access to sensitive attributes through C-level attribute access. This could lead to significant information exposure, as it permits prompt-influenced code to read critical class and object attributes without a full execution chain. Organizations using versions prior to 1.6.59 should prioritize updating to mitigate the risk of data leakage.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59.