The Agent Skills Directory

[SAFE]: The skill is entirely composed of Markdown documentation and behavioral instructions for the AI agent. It does not include any scripts, executables, or binary files.
[PROMPT_INJECTION]: The instructions provided in SKILL.md are designed to guide the agent's persona and logic (Agentic Protocol) without attempting to bypass safety filters or ignore system instructions.
[DATA_EXFILTRATION]: No network-related commands (curl, wget) or sensitive file path access (e.g., .ssh, .aws) were found in the provided files.
[REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of remote scripts. The 'npx' command mentioned in the README is an installation instruction for the user and not part of the skill's runtime logic.
[NO_CODE]: The skill does not rely on Python or Node.js scripts, significantly reducing the attack surface for code-based vulnerabilities.

webb-perspective