The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to open the resulting HTML presentations using system-specific openers like open on macOS, xdg-open on Linux, and start on Windows. It also suggests using python3 for extraction and mentions using browser automation for verification tasks.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the python-pptx library if it is not present on the system to facilitate the conversion of PowerPoint files.
[PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill processes content from external .ppt and .pptx files, which could contain malicious instructions designed to manipulate the presentation generation logic.
Ingestion points: Data extracted from user-provided PowerPoint files (text, notes, images).
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore embedded commands within the extracted content.
Capability inventory: File writing (presentation.html), Python execution for extraction, and shell command execution for opening files.
Sanitization: There are no explicit requirements to sanitize or validate the extracted text before it is interpolated into the HTML/JavaScript presentation code.

frontend-slides