The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands such as docker info, docker build, docker run, and docker-compose config to perform environment detection and configuration validation. These operations are aligned with the skill's primary purpose and are executed within the user's local context.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points include local project files like Dockerfiles and Compose files identified via filesystem discovery in SKILL.md. Boundary markers or explicit instructions to disregard embedded commands in those files are not present. Capability inventory includes docker build, docker run, and docker exec which execute logic defined in the ingested files. No specific sanitization or validation of the file contents is performed prior to building or running the containers.
[EXTERNAL_DOWNLOADS]: The skill documentation and snippets reference official container images from trusted organizations and well-known services, including Docker Hub and Google Container Registry. These references are used for providing industry-standard templates and do not involve downloading or executing untrusted remote code.

docker-expert