The Agent Skills Directory

[PROMPT_INJECTION]: No patterns of instruction overrides, safety bypasses, or jailbreak attempts were detected. The workflow uses standard instructional language to guide the agent through a scaffolding process.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path access, or unauthorized network transmission patterns were identified. All links in the skill are relative and internal to the skill directory.
[COMMAND_EXECUTION]: The skill does not execute any shell commands or scripts. Reference documentation mentions tool capabilities (e.g., 'allowed-tools') for metadata specification and educational purposes, but no executable code is included.
[NO_CODE]: The skill is entirely composed of Markdown files. No Python scripts, Node.js packages, or binary executables are included in the distribution.
[SAFE]: The skill's author metadata aligns with the provided context, and all external references point to legitimate vendor-related documentation patterns.

create-skill