CyberRota Analysis
AI-GeneratedCodeWhale versions 0.8.41 to 0.8.63 are vulnerable due to a flaw in the exec_shell_interact tool, which allows unapproved code execution in long-running interactive shells, such as Python REPL or SSH sessions. This vulnerability enables attackers to execute arbitrary commands at the privilege level of the approved process if they can inject malicious instructions through untrusted content. Organizations using affected versions should prioritize patching to version 0.8.64 to mitigate the risk of unauthorized command execution.
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
CodeWhale versions >= 0.8.41 and < 0.8.64 contain a vulnerability in the exec_shell_interact (alias exec_interact) tool, whose approval_requirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an already-approved long-running interactive shell (e.g., a python3 -i REPL, mysql, ssh, or sudo -i session) without any approval prompt. An attacker who can inject instructions via untrusted content the agent ingests (a fetched page, MCP result, or repo file) can cause commands to run at the privilege level of that approved process. Fixed in 0.8.64.