Pentest Commands

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt contains examples that embed plaintext credentials and passwords directly into commands (e.g., set SMBPass pass, --data="user=admin&pass=test", msfconsole lines), which instructs an agent to include secret values verbatim in generated commands and thus creates an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content explicitly provides actionable offensive commands that enable remote code execution and backdoors (reverse shells, msfvenom payloads, Metasploit exploits and handlers), credential theft/brute‑forcing (hydra, john, smb/ssh brute scripts), and data exfiltration (sqlmap dumping/os-shell, nikto/scan scripts), which are high‑risk patterns facilitating deliberate malicious activity.