The Agent Skills Directory

[SAFE]: The skill is authored by the official vendor 'hostinger' and is designed specifically to interact with their hosting infrastructure using authorized API tools. All external references and tools are vendor-aligned and serve the primary purpose of the skill.\n- [COMMAND_EXECUTION]: The skill utilizes standard system utilities such as curl, zip, and git archive to package and upload user project files. These operations are restricted to the local environment and the vendor's authenticated upload endpoints.\n- [DATA_EXPOSURE]: The skill reads configuration files like .env and package.json to synchronize environment variables and deployment settings. This is a core part of its functionality and includes explicit safety instructions for the agent to avoid committing sensitive files or leaking secret values to the user.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes project files (Ingestion points: package.json, .env, .hostinger/site.json) to determine deployment settings. Capability inventory: File writes, network ops (curl), and command execution. While no explicit boundary markers are used, the skill instructs the agent to validate settings and follow secure practices for secret handling.

deploy-to-hosting