The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to analyze the environment and validate container configurations. This includes docker version, docker info, docker build, docker run, and docker exec. These commands are used for their intended purpose of diagnosing and testing Docker environments.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted local configuration files which could theoretically influence the agent's actions or result in code execution during build/run cycles.
Ingestion points: The skill searches for and reads local Dockerfile and docker-compose.yml files.
Boundary markers: None observed; the skill processes file content directly for analysis.
Capability inventory: The skill has the ability to execute docker build, docker run, and docker exec, which can execute code defined in the ingested files.
Sanitization: No specific sanitization or validation of the content within the Docker configuration files is performed before execution.

docker-expert