The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool and local Python scripts (scripts/generate_deploy.py, scripts/validate_deploy.py) to automate tasks. This is expected behavior for a deployment engineering skill.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through its artifact generation process. User-supplied strings are written to a markdown file without escaping.
Ingestion points: The --name, --env, and --owner arguments in scripts/generate_deploy.py allow user input to be included in generated files.
Boundary markers: The generated deploy-plan.md does not use specific delimiters or instructions to prevent the agent from following embedded commands if it later reads the file.
Capability inventory: The skill possesses Read, Write, Edit, and Bash tools as defined in SKILL.md.
Sanitization: No sanitization or validation is performed on the inputs before they are written to the deployment plan.

deployment-engineer