Description
Cybersecurity AI (CAI) is a framework for AI Security. In versions up to and including 0.5.10, the CAI (Cybersecurity AI) framework contains multiple argument injection vulnerabilities in its function tools. User-controlled input is passed directly to shell commands via `subprocess.Popen()` with `shell=True`, allowing attackers to execute arbitrary commands on the host system. The `find_file()` tool executes without requiring user approval because find is considered a "safe" pre-approved command. This means an attacker can achieve Remote Code Execution (RCE) by injecting malicious arguments (like -exec) into the args parameter, completely bypassing any human-in-the-loop safety mechanisms. Commit e22a1220f764e2d7cf9da6d6144926f53ca01cde contains a fix.
Problem types
CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Product status
References
github.com/...cs/cai/security/advisories/GHSA-jfpc-wj3m-qw2m
github.com/...ommit/e22a1220f764e2d7cf9da6d6144926f53ca01cde
github.com/...7e4/src/cai/tools/reconnaissance/filesystem.py