The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local shell commands to detect the environment and analyze project structure.
Evidence: Uses docker --version, docker info, docker context ls, and find commands to locate Dockerfiles, Compose files, and .dockerignore files.
[DYNAMIC_EXECUTION]: The skill performs validation by building and running containers based on the user's project files.
Evidence: Executes docker build, docker history, docker scout, docker run, docker exec, and docker-compose config to verify the validity and security of configurations.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted local data from project files to determine its advice and actions.
Ingestion points: Automatically searches for and reads Dockerfile*, *compose*.yml, and .dockerignore files within the working directory.
Boundary markers: The instructions do not define explicit delimiters or "ignore embedded instructions" warnings when processing the contents of these files.
Capability inventory: The skill has the ability to execute shell commands, build images, run containers, and inspect process lists within containers.
Sanitization: No explicit sanitization, filtering, or strict schema validation is mentioned for the content of the Docker-related files it ingests.

docker-expert