The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands (find, grep) and Docker CLI tools (docker build, docker run, docker exec) to perform environment discovery and build validation. These capabilities are necessary for the skill's functionality as a containerization expert.
[DATA_EXPOSURE]: The skill executes docker info and docker context ls to retrieve environment metadata. This information is used for diagnostic purposes and is not transmitted outside the local environment.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files (Dockerfiles, Compose YAML) which could theoretically contain malicious content if sourced from untrusted third parties.
Ingestion points: Reads files matching Dockerfile* and *compose*.yml in the current working directory.
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore embedded comments or instructions in these files.
Capability inventory: Includes docker build, docker run, and docker exec which provide significant control over the container environment.
Sanitization: Absent; the skill directly processes the contents of found Docker configuration files during build and validation phases.

docker-expert