The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill includes instructions to download and execute the official rootless Docker installation script from Docker's verified domain (get.docker.com) using a pipe to shell (curl | sh).
[COMMAND_EXECUTION]: The auditing scripts scripts/agent.py and scripts/process.py execute the docker info command via the subprocess module to collect system metadata for security compliance verification.
[INDIRECT_PROMPT_INJECTION]: The skill processes external configuration data and tool outputs, creating an attack surface where malicious data in those sources could potentially influence the agent's reasoning.
Ingestion points: The skill reads configuration data from /etc/docker/daemon.json and captures output from the docker info command in scripts/agent.py and scripts/process.py.
Boundary markers: Absent. The skill does not employ specific delimiters or instruction-isolation markers when presenting this external data to the agent.
Capability inventory: The skill possesses capabilities for reading/writing local files and executing system commands via the Docker CLI.
Sanitization: Absent. While the scripts utilize JSON parsing to validate structure, they do not sanitize content for downstream prompt safety, relying on the integrity of the host environment.

hardening-docker-daemon-configuration