The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell and Docker commands to analyze the environment and validate project configurations.
Environment detection is performed via docker version, docker info, and docker context ls.
File discovery utilizes find to locate Dockerfiles and Compose configurations.
Validation steps involve executing docker build, docker run, and docker-compose config on local files.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from the Docker-related files it processes.
Ingestion points: The skill reads local files like Dockerfile and docker-compose.yml identified by the find command in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are used to separate untrusted file content from the agent's instructions during analysis.
Capability inventory: The agent has the ability to execute shell commands, build images, and run containers based on the analyzed file content.
Sanitization: There is no evidence of content filtering or sanitization before the agent processes the file contents.
[EXTERNAL_DOWNLOADS]: The skill references base images from well-known registries for its optimization examples.
Examples reference node:18-alpine from Docker Hub and gcr.io/distroless/nodejs18-debian11 from Google Container Registry.
These references are used for demonstrating best practices in multi-stage builds and image hardening.

docker-expert