The Agent Skills Directory

[COMMAND_EXECUTION]: Uses local shell commands including docker info, docker ps, docker images, and find to identify the environment and project structure.- [COMMAND_EXECUTION]: Performs docker build and docker run on local project files to validate the functionality and security of container configurations.- [PROMPT_INJECTION]: Contains potential for indirect prompt injection as it processes local files like Dockerfile and docker-compose.yml which are untrusted.
Ingestion points: Uses find and internal read tools to ingest contents from Dockerfile and compose yaml files.
Boundary markers: Does not utilize explicit boundary markers or 'ignore' instructions when reading file content.
Capability inventory: Possesses the ability to execute docker and bash commands in the host environment.
Sanitization: No validation or sanitization is performed on the content of the project files before they are processed by the agent context.

docker-expert