skills/davepoon/buildwithclaude/init/Gen Agent Trust Hub

init

Fail

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill uses a highly dangerous pattern to install software by downloading a remote shell script and piping it directly into the bash interpreter.
  • Evidence: curl -fsSL https://raw.githubusercontent.com/7xuanlu/origin/v0.6.1/install.sh | bash in SKILL.md.- [EXTERNAL_DOWNLOADS]: The skill downloads code from a GitHub account (7xuanlu) that is not associated with a recognized trusted vendor or well-known service.- [COMMAND_EXECUTION]: The skill executes various system commands to modify the environment and manage background processes.
  • Modifies the system PATH using export PATH="$HOME/.origin/bin:$PATH".
  • Uses origin install to create a launchd persistence item and start a background daemon.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/7xuanlu/origin/v0.6.1/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Jun 13, 2026, 07:51 AM
Security Audit — agent-trust-hub — init