advanced-features-2025

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides multiple bash scripts designed to be executed via event-based hooks for standard development tasks such as code linting, automated testing, and formatting. These are documented as automation tools within the agent's workflow.
  • [EXTERNAL_DOWNLOADS]: Integration patterns for the Model Context Protocol (MCP) suggest fetching and running servers from public registries using npx. The examples focus on well-known services and official protocol implementations.
  • [SAFE]: The skill includes security-focused scripts such as validate-command.sh, which implements a blocklist for dangerous shell patterns like recursive root deletion, and pre-commit-check.sh, which identifies staged sensitive files (e.g., .env or private keys) to prevent accidental exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 12:06 PM