aircrack-ng

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This content explicitly instructs on active Wi‑Fi attacks (monitor mode, killing network services, deauthentication to force handshakes, and offline WPA cracking), which is high-risk and easily abused for unauthorized access; no hidden backdoors, external data exfiltration, credential-harvesting code, or obfuscated/remote‑execution payloads were found.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The prompt explicitly instructs the agent to run privileged, state-changing commands (e.g., "airmon-ng check kill", "airmon-ng start/stop", aireplay-ng deauth) that kill network services, change interface modes, and enable active wireless attacks, which require elevated privileges and modify the host system's state.