The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx in scripts/validate_mermaid_markdown.sh to fetch and execute the @mermaid-js/mermaid-cli package from the npm registry. This is a standard method for accessing official Mermaid validation tools.
[COMMAND_EXECUTION]: The skill instructs the agent to run local bash scripts (assess_mermaid_density.sh and validate_mermaid_markdown.sh) to analyze and render diagrams. These scripts interact with the file system to read markdown files using tools like awk and rg.
[INDIRECT_PROMPT_INJECTION]: The skill processes markdown files that may contain untrusted Mermaid diagram definitions, which are passed to external tools for parsing. 1. Ingestion points: The validation scripts ingest user-provided markdown files as their primary input. 2. Boundary markers: There are no explicit instructions or delimiters defined to prevent the Mermaid parser from interpreting malicious instructions hidden within diagram code. 3. Capability inventory: The skill has the capability to read files via awk and rg, and execute external code through npx (referencing the Mermaid CLI). 4. Sanitization: No sanitization is performed on the input markdown content before it is passed to the Mermaid CLI validator.

mermaid-diagrams