Cybersecurity AI vulnerable to command Injection through argument injection in find_file Agent tool
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 …
Severity critical: primary CNA CVSS 9.7 v3.1 (worst CNA-provided scenario) Not listed in this KEV snapshot. Forecast present in this snapshot.
Published 2026-01-30T20:15:51.772Z. Updated 2026-02-02T18:01:06.518Z.