ethical-hacking-methodology

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's mandatory gate requires the agent to "show the exact command(s)" using user-supplied targets/accounts (and the doc contains an example that passes a plaintext password on the command line), which would force the LLM to include secret values verbatim in its output.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document contains explicit, actionable instructions for remote code execution (reverse shells), establishing persistent backdoors (meterpreter persistence, SSH key/crontab planting), credential-stealing/brute-force and data extraction—high risk for misuse despite its authorized-use framing.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill includes explicit instructions to create persistence and modify system files (e.g., appending to /etc/crontab, adding SSH keys, running dd to raw devices, Meterpreter persistence, setting root password), which require elevated privileges and change the host system state.