The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the Kamal deployment tool using gem install kamal and optionally via a Docker container from ghcr.io/basecamp/kamal:latest, which is a well-known repository from Basecamp. It also instructs the agent to install Docker on servers using the official installation script from get.docker.com.
[COMMAND_EXECUTION]: The skill directs the agent to execute various shell commands required for deployment, including kamal init, kamal setup, and kamal server bootstrap. These commands involve establishing SSH connections and managing containers on remote servers.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it is instructed to ingest and act upon the contents of config/deploy.yml and .kamal/secrets.
Ingestion points: Reads and extracts configuration data from config/deploy.yml and .kamal/secrets.
Boundary markers: No specific boundary markers or instructions to ignore embedded directives within these files are provided.
Capability inventory: The skill possesses the capability to execute shell commands, perform remote server administration, and interact with network services.
Sanitization: There is no evidence of validation or sanitization of the configuration file content before it is incorporated into the agent's task flow.

setup