The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill downloads and executes an installation script (install.sh) from the vendor's official GitHub repository (rudderlabs/rudder-iac). This is a standard installation pattern for CLI tools.
[EXTERNAL_DOWNLOADS]: The skill fetches release archives and checksum files directly from GitHub Releases (github.com/rudderlabs/rudder-iac/releases). These downloads are authenticated via the vendor's own infrastructure.
[COMMAND_EXECUTION]: The skill executes shell commands to check for the existence of the CLI, modify file permissions, and verify versioning. It also instructs users on how to update their shell profile (PATH variable) for persistence.
[INDIRECT_PROMPT_INJECTION]: The skill processes output from external commands and APIs, creating a potential surface for indirect injection.
Ingestion points: Command output from rudder-cli workspace info --json and curl responses from GitHub API/releases.
Boundary markers: None explicitly defined in the prompt instructions for processing tool output.
Capability inventory: Full shell access (Bash), file system modification (Write, Edit), and network access via curl.
Sanitization: The manual installation workflow includes a robust SHA256 checksum verification step to ensure the integrity of the downloaded archive before extraction.

rudder-cli-setup