The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs various Docker and shell operations, including docker build, docker run, docker exec, and find. These commands are used to analyze project structures, build images, and validate container runtime behavior, which are essential functions for a Docker expert tool.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes local project files to inform its actions.\n
Ingestion points: The skill searches for and reads local Dockerfile and docker-compose.yml files using find and grep.\n
Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within the ingested configuration files.\n
Capability inventory: The skill has the capability to build and run containers based on the ingested files, which could execute logic defined within those files.\n
Sanitization: No sanitization or content validation is performed on the files before they are used in Docker commands.\n- [SAFE]: The skill references base images and registries from trusted and well-known providers, such as PostgreSQL on Docker Hub and Distroless images from Google Container Registry (gcr.io).

docker-expert