The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use operating system commands such as open (macOS), xdg-open (Linux), and start (Windows) to open generated HTML presentation files automatically upon completion.
[EXTERNAL_DOWNLOADS]: The instructions specify that generated presentations may fetch resources from external font services including Google Fonts and Fontshare.
[REMOTE_CODE_EXECUTION]: The skill relies on python-pptx for PowerPoint conversion tasks. If the library is missing, the skill instructs the agent to ask the user to install it or attempt a manual workflow, which involves managing external software dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill parses content from external .ppt and .pptx files to generate HTML slides. This represents a vulnerability surface where malicious instructions embedded in a presentation could be interpreted by the agent during the conversion process.
Ingestion points: PowerPoint files (.ppt, .pptx) processed during the "PPT / PPTX Conversion" workflow.
Boundary markers: No specific delimiters or "ignore instructions" warnings are mentioned for handling extracted text.
Capability inventory: The skill uses python3 subprocesses to execute extraction logic and writes generated HTML/JS files to the local file system.
Sanitization: The skill does not explicitly describe sanitization or filtering of the extracted slide content before it is interpolated into the final HTML presentation.

frontend-slides