The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides various shell (.sh) and PowerShell (.ps1) scripts designed to manage Docker containers and services. These scripts execute commands such as docker-compose up, docker exec, and mysqldump to perform deployment and database backup tasks. These operations are the primary function of the skill and are performed using standard system utilities.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a template generator that incorporates external data, such as task documentation and project names, into deployment configurations.
Ingestion points: The skill processes task documents and configuration files (referenced in SKILL.md).
Boundary markers: There are no explicit delimiters used to separate processed data from instructions.
Capability inventory: The skill has the ability to generate and execute shell commands and write to the local file system through its generated scripts.
Sanitization: Project-specific variables like PROJECT_NAME are used within the scripts without explicit validation, which is common for developer-oriented scaffolding tools.
[SAFE]: The external resources referenced in the Docker configurations, such as mysql:8.0, redis:7-alpine, and nginx:alpine, are official images from well-known and trusted providers. The skill also includes security headers in its Nginx templates and explicitly warns against committing sensitive .env files to version control.

proj-deploy