The Agent Skills Directory

COMMAND_EXECUTION (LOW): The file scripts/validate.sh performs local diagnostic checks using commands like docker version, docker info, and docker ai --help to ensure the environment is correctly configured. These are non-destructive, standard verification operations.
PROMPT_INJECTION (LOW): The skill documentation and integration scripts (e.g., in TOOLS.md and examples.md) encourage piping local files like Dockerfile or logs.txt into the docker ai command. This creates an indirect prompt injection surface.
Ingestion points: Files are ingested via shell redirection (<) in scripts/review-dockerfile.sh, scripts/validate-compose.sh, and several examples.
Boundary markers: The prompts do not use delimiters or explicit instructions to ignore potentially malicious embedded content within the analyzed files.
Capability inventory: The tool is designed to generate Dockerfiles, Compose configurations, and troubleshooting advice based on the input.
Sanitization: There is no evidence of pre-processing or sanitization of the file content before it is processed by the AI service.

aiops-gordon