dcg
A reusable agent skill published by dicklesworthstone/destructive_command_guard.
How do I install this agent skill?
npx skills add https://github.com/dicklesworthstone/destructive_command_guard --skill dcgIs this agent skill safe to install?
- Gen Agent Trust Hubfail
The 'dcg' skill is a high-performance safety hook for AI agents designed to block destructive shell commands. It includes installation scripts that use remote code execution from the author's own repository and well-known services like Rustup. However, it also references a third-party installation script for an external tool and contains a maintenance script that executes commands derived from remote data. The skill also introduces a surface for indirect prompt injection and minor persistence through shell configuration modifications.
- Socketfail
7 alerts: gptMalware, gptAnomaly, gptSecurity
- Snykpass
Risk: LOW · No issues
- Runlayerfail
117/447 files flagged
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/dicklesworthstone/destructive_command_guard/dcg">View dcg on skillZs</a>