The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the puppeteer package from the npm registry during the setup process. This is a legitimate and well-known library used for the skill's core function of rendering HTML slides to PNG images.
[COMMAND_EXECUTION]: The skill executes multiple shell commands to manage its lifecycle, including npm install for setup, node to run the rendering logic, and system utilities like open and AppleScript to display the finished slides and open the file manager for delivery.
[PROMPT_INJECTION]: The skill accepts a topic or description from the user to generate slide content, creating a vulnerability surface for indirect prompt injection. Malicious instructions within the topic could attempt to override the agent's behavior during the content generation phase.
Ingestion points: User-provided topic input passed to the /carousel command.
Boundary markers: The instructions do not implement specific delimiters or 'ignore' instructions to isolate the user-provided topic from the generation prompt.
Capability inventory: The skill has the capability to write to the file system, install npm packages, and execute shell commands.
Sanitization: There is no mention of input validation, sanitization, or filtering applied to the user-supplied topic before it is processed by the model.

carousel