The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it is designed to ingest and process data from external PowerPoint (.ppt, .pptx) files and user-supplied notes without explicit boundary protection.
Ingestion points: The skill reads content from external .ppt and .pptx files via Python scripts and processes user-pasted text drafts.
Boundary markers: No delimiters or instructions to ignore embedded commands are present in the workflow for handling external file content.
Capability inventory: The skill can write files to the local filesystem (HTML, assets), execute Python scripts, and invoke system-level shell commands to open files.
Sanitization: There are no instructions to sanitize, escape, or validate the content extracted from external files before the agent processes it or incorporates it into generated code.
[COMMAND_EXECUTION]: The skill instructs the agent to execute OS-specific commands (open on macOS, xdg-open on Linux, and start on Windows) to automatically open the generated presentation files for the user. While this is a convenience feature for a presentation tool, it involves executing shell commands with generated file paths.
[EXTERNAL_DOWNLOADS]: The workflow suggests installing the python-pptx library using a package manager if it is not already available on the system. This is a standard dependency for the skill's primary PowerPoint conversion feature.

frontend-slides