The Agent Skills Directory

[SAFE]: The skill adheres to security best practices by using yaml.safe_load for all YAML parsing, which prevents unsafe deserialization of arbitrary Python objects.
[SAFE]: File integrity is protected through an atomic write pattern; the skill renders content to a temporary file and uses os.replace for the final update, preventing data corruption during failures.
[SAFE]: Output sanitization filters (markdown_cell, markdown_inline) are employed to escape control characters like pipes (|) and normalize line breaks, ensuring that untrusted data cannot break the structure of the rendered Markdown tables.
[SAFE]: The dashboard loader implements strict schema validation that rejects unknown YAML keys with specific path information, providing robust defense against malformed or malicious configuration data.

mols-markdown-dashboard