skills/goldk3y/skills/build-eve-agent/Gen Agent Trust Hub

build-eve-agent

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation from 'https://eve.dev/llms.txt' to ground agent implementation in the latest framework standards, ensuring code quality and compatibility.
  • [COMMAND_EXECUTION]: Runs a local 'scripts/preflight.sh' to verify the environment (Node.js version, Git status, and package manager) before building the agent. The script is read-only and does not modify the system.
  • [DATA_EXFILTRATION]: Audits the presence of necessary API keys (e.g., ANTHROPIC_API_KEY) in the environment to ensure readiness, but explicitly avoids printing or transmitting secret values, maintaining credential security.
  • [REMOTE_CODE_EXECUTION]: Uses standard package management commands like 'npx eve@latest init' to bootstrap the agent project. This is a legitimate and expected operation for the skill's primary function of building AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 05:26 AM
Security Audit — agent-trust-hub — build-eve-agent