cmdi-command-injection

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Multiple URLs point to attacker-controlled hosts or direct PowerShell payloads and an exploit GitHub repo (ATTACKER/attacker/BURP_COLLAB_HOST/attacker.com/neex repo), which are high-risk download/execution sources suitable for distributing malware.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit attacker playbook that instructs how to perform OS command injection, data exfiltration, remote code execution (reverse shells), credential/secret discovery, environment-based persistence, and obfuscation techniques — clearly enabling malicious activity.

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 explicitly instructs using command-injection payloads, writing/modifying system files (e.g., /var/www/html/.htaccess, cmd.sh), LD_PRELOAD/so upload, reverse shells, and abusing the Docker/socket to bind-mount the host — all of which push an agent to obtain arbitrary code execution and modify the machine state.