performing-physical-intrusion-assessment

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows reading and cloning RFID badges and example commands that embed badge identifiers, FC/CN values and keys (and C2 URLs) directly into CLI payloads, which requires the LLM to handle and output secret/credential values verbatim.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). The first URL is a direct PowerShell stager (.ps1) hosted on a C2-style host and is highly suspicious/malicious, while the second URL is benign MITRE ATT&CK documentation; overall the presence of the stager makes this set high risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document contains explicit, deliberate offensive techniques — badge cloning, lock bypassing, credential capture, rogue device deployment (LAN Turtle reverse SSH to c2.redteam.com, WiFi Pineapple evil‑twin), and a USB Rubber Ducky payload that downloads/executes a stager (https://c2.redteam.com/stager.ps1) — which constitute backdoors/remote code execution, credential theft, and data exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill contains runtime commands that download/execute remote code and connect to a C2 host (powershell IEX download from https://c2.redteam.com/stager.ps1 and LAN Turtle SSH to c2.redteam.com), so the external URL(s) directly control execution during runtime.