agentic-harness-engineering

Fail

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The installation instructions for Linux environments include the use of sudo apt install -y tmux. Using sudo allows the skill instructions to execute commands with administrative privileges on the host system.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a source code repository from an external GitHub account (https://github.com/china-qijizhifeng/agentic-harness-engineering.git). This repository is not associated with a known trusted organization and contains the core logic executed by the skill.
  • [REMOTE_CODE_EXECUTION]: The skill uses a piped-to-shell pattern (curl -LsSf https://astral.sh/uv/install.sh | sh) to install the 'uv' package manager. While 'astral.sh' is the official domain for this well-known tool, executing remote scripts directly in the shell is a high-risk pattern that bypasses package integrity checks.
Recommendations
  • HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 16, 2026, 10:19 AM
Security Audit — agent-trust-hub — agentic-harness-engineering