hackingtool

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.85). These links point to a GitHub repository for an offensive "hackingtool" and include a direct raw install.sh intended to be run (curl|bash with sudo); running unreviewed remote scripts and a toolkit that installs exploits/RATs/executables is a high-risk distribution vector for malware or privilege abuse.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High-risk dual-use aggregator that explicitly bundles and automates offensive capabilities (phishing toolkits, RATs, C2 frameworks, exploit frameworks, DDOS tools, payload creators) and uses risky install patterns (curl|bash) — making it easily usable for credential theft, remote code execution, backdoors, and data exfiltration if abused.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill includes runtime install commands that fetch and execute remote code — notably curl -sSL https://raw.githubusercontent.com/Z4nzu/hackingtool/master/install.sh | sudo bash and git clone https://github.com/Z4nzu/hackingtool.git followed by python3 hackingtool.py — so external content will be executed locally.

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 running privileged install commands (curl ... | sudo bash, sudo python3 ...), batch-installing tools and launching post-exploitation/C2/RAT tooling — all of which request/require sudo and modify the host state, so it pushes the agent to obtain elevated privileges and change the machine.