The Agent Skills Directory

[SAFE]: The skill provides extensive documentation for various Mermaid diagram types, including flowcharts, sequence diagrams, class diagrams, etc.
[EXTERNAL_DOWNLOADS]: The documentation references external resources such as mermaid.js.org, mermaid.live, GitHub repositories, and CDNs like JSDelivr and Cloudflare. These are well-known and trusted services used for documentation, icon fonts (FontAwesome), and style typesetting (KaTeX).
[COMMAND_EXECUTION]: The documentation mentions CLI tools like mmdc (@mermaid-js/mermaid-cli) and Docker usage as part of its technical guides for users. No instructions were found directing the agent to execute these commands autonomously.
[DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were identified. Interactive diagram features (like click or callback syntax) are documented as language features, not as instructions for the agent to harvest data.
[PROMPT_INJECTION]: The instructions are focused on producing correct Mermaid syntax and do not contain any attempt to override system safety guidelines or extract system prompts.

mermaid