The Agent Skills Directory

[SAFE]: No malicious code or patterns were detected. The skill implementation is a legitimate tool for document generation and project management.
[COMMAND_EXECUTION]: The provided Python scripts (e.g., ppt_manager.py, html_to_ppt.py) are designed for command-line use by an AI agent. They handle project initialization, file addition, and final PPTX building through standard argument parsing. No use of dangerous shells or unsanitized system calls was found.
[DATA_EXFILTRATION]: The skill operates entirely within a local project directory structure. There are no network calls, external API requests, or attempts to access sensitive system files (e.g., SSH keys, credentials).
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on enforce design quality, component diversity, and tool-specific workflows. There are no patterns attempting to bypass agent safety filters or override core behavioral guidelines.
[REMOTE_CODE_EXECUTION]: The skill uses the standard xml.etree.ElementTree library for XML parsing and python-pptx for presentation generation. It does not employ eval(), exec(), or dynamic code loading mechanisms that could be exploited by remote input.

ppt-maker