skills/evo-hq/evo/infra-setup/Gen Agent Trust Hub

infra-setup

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run commands for configuring the evo CLI and installing provider SDKs. It explicitly mandates that these operations must not be silent and requires the agent to ask the user for confirmation before proceeding with any installation.
  • [EXTERNAL_DOWNLOADS]: The instructions reference the installation of evo-hq-cli and its optional provider extras (e.g., [modal], [aws], [e2b]), along with official SDKs like boto3. These packages are recognized as vendor-owned resources or official libraries for well-known services.
  • [CREDENTIALS_UNSAFE]: The skill provides guidance on managing authentication for cloud providers, including API keys and SSH keys. It emphasizes using official auth commands (e.g., modal token new, az login) and environment variables. It follows best practices by instructing that these credentials should be kept separate from the runtime environment where experiments or benchmarks are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:41 PM
Security Audit — agent-trust-hub — infra-setup