The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes several shell commands to interact with the Docker environment and project files. These include informational commands like docker info and docker ps, as well as build and validation commands like docker build, docker run, and docker exec used on test containers for verification purposes.
[EXTERNAL_DOWNLOADS]: The skill performs Docker build and run operations which involve pulling container images from remote registries. These actions are standard for Docker-related tasks and the skill references well-known, trusted sources like Google's distroless images and official Alpine-based node images.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risk as it reads local configuration files to provide optimization advice.
Ingestion points: The skill reads Dockerfile and docker-compose files from the local filesystem during its initial analysis phase in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the analyzed files are present.
Capability inventory: The skill can execute high-capability shell commands including docker run and docker exec across its validation workflows.
Sanitization: The skill does not sanitize or filter the content of the files it reads before processing them.

docker-expert