The Agent Skills Directory

[SAFE]: The skill instructions and scripts focus on legitimate cloud infrastructure management and security hardening. All identified behaviors align with the stated purpose of provisioning and securing Hetzner Cloud servers.
[COMMAND_EXECUTION]: The skill uses established tools such as the hcloud CLI, ssh, ufw, and fail2ban to perform its tasks. The provided scripts/verify.sh is a read-only bash script designed to lint configuration files for security best practices without performing network operations or file writes.
[EXTERNAL_DOWNLOADS]: References official and well-known sources for software installation, including the official Hetzner Cloud CLI GitHub repository and the standard Docker installation script. These references are used for legitimate setup purposes.
[DATA_EXFILTRATION]: There is no evidence of unauthorized data access, credential harvesting, or transmission of sensitive information to external domains.
[PROMPT_INJECTION]: The skill does not contain any instructions attempting to override agent safety guidelines, bypass constraints, or manipulate core behavior.

hetzner