The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions require downloading the complete toolset from an external GitHub repository (github.com/ryanbbrown/revealjs-skill). This introduces a dependency on the availability and security of a third-party source not categorized as a trusted vendor.
[REMOTE_CODE_EXECUTION]: The installation process utilizes npx skills add to fetch and integrate remote content. This pattern facilitates the execution of remote scripts and code within the agent's environment.
[COMMAND_EXECUTION]: The skill provides specific shell commands for the agent to run in the chat context. These commands interact with the file system to check for existence and inspect the contents of skill metadata files (e.g., ~/.agents/skills/revealjs/SKILL.md).
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-provided content to scaffold slides and generate Reveal.js presentations.
Ingestion points: Data used to create themes, multi-column layouts, and Chart.js charts is processed from input prompts (found in SKILL.md).
Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided files.
Capability inventory: The skill executes Node.js scripts and utilizes npx for PDF generation and screenshot capture.
Sanitization: There are no documented sanitization or escaping mechanisms to prevent malicious content in the input from becoming executable in the generated HTML/JS environment.

revealjs-skill