The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses platform-specific shell commands (open on macOS, xdg-open on Linux, and start on Windows) to automatically open the generated HTML presentation in the user's browser. This is a standard convenience feature for localized document generation tools.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the python-pptx library if it is not present in the environment. This library is a well-known, legitimate dependency required for the skill's PowerPoint conversion functionality.
[DATA_EXFILTRATION]: The skill is designed to read local files (.ppt and .pptx) for the purpose of content extraction and conversion. This access is limited to the conversion workflow and the data is used to generate the local HTML output.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it incorporates untrusted data from user-supplied notes and converted PowerPoint files directly into generated HTML and JavaScript code.
Ingestion points: User-provided notes, slide content, and data extracted from .ppt or .pptx files (SKILL.md).
Boundary markers: There are no explicit instructions for the agent to use delimiters or safety guards when interpolating user content into code.
Capability inventory: The skill performs file system writes, executes shell commands for file opening, and runs Python scripts (SKILL.md).
Sanitization: The skill does not mention specific sanitization, escaping, or validation steps for content processed during the conversion or enhancement workflows.

frontend-slides