The Agent Skills Directory

[SAFE]: The skill provides a legitimate framework for skill development, consisting of educational guidelines and local helper scripts.
[COMMAND_EXECUTION]: The skill includes Python scripts (init_skill.py, package_skill.py, quick_validate.py) designed to manage the development lifecycle of other skills. These scripts perform local file system operations such as directory creation, file writing, and archiving (ZIP), which are standard for project initialization and packaging tools.
[DYNAMIC_EXECUTION]: The init_skill.py script generates a boilerplate Python file from an internal template string. This is a common development utility pattern and does not involve the execution of untrusted external code or data.
[DATA_EXFILTRATION]: No network-enabled operations (e.g., use of requests, urllib, or curl) were detected. The skill operates entirely on the local file system and does not access sensitive user directories like .ssh or .aws.
[PROMPT_INJECTION]: The content in SKILL.md and the reference files consists of procedural instructions for the agent. There are no attempts to bypass safety filters, extract system prompts, or override agent behavior through injection markers.

skill-creator