The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local Node.js scripts (e.g., scaffold-html.ts and validate-html.ts) to automate the creation of project structures and the validation of generated HTML artifacts. These scripts perform file system operations, such as directory creation and file writing, while implementing safety checks like preventing overwrites through symbolic links.
[DYNAMIC_EXECUTION]: The validation logic in scripts/validation/validate-embedded-javascript.ts employs the node:vm module to compile and verify the syntax of inline scripts without executing them. Additionally, it uses node:child_process.spawnSync to run the Node.js parser in check-only mode (--check) to validate JavaScript modules.
[INDIRECT_PROMPT_INJECTION]: As the skill renders content provided by other workflows, it acts as an ingestion point for AI-generated data. While it includes HTML escaping for metadata and a comprehensive validation layer to identify and block external resources or malicious script patterns, it remains inherently linked to the safety of the input data it visualizes.
[SAFE]: The skill implements significant security best practices, including a mandatory validation step that detects and errors on external network dependencies, CDNs, or remote script imports. It is designed to produce completely offline, portable artifacts, thereby minimizing the attack surface associated with external data exfiltration or remote code loading.

ptlam-visualizing-with-html