The Agent Skills Directory

[SAFE]: The skill's primary purpose is educational, providing templates and guides for skill development. Analysis of all files, including scripts and reference documents, shows no malicious intent or suspicious behavior.
[COMMAND_EXECUTION]: The skill provides templates and instructions for executing local shell commands (e.g., git, mkdir) and Python scripts (e.g., scripts/analyze.py). These are presented as standard examples of the platform's capabilities.
[PROMPT_INJECTION]: The templates in references/templates.md demonstrate dynamic context injection (indirect prompt injection surface) by interpolating command output into prompts.
Ingestion points: references/templates.md (interpolating results of commands like git log into the context).
Boundary markers: None are present in the provided templates to delimit external data from instructions.
Capability inventory: The skill framework allows for shell command execution and file system access as described in SKILL.md.
Sanitization: No sanitization or escaping logic is included in the instructional templates for command output.

create-skill