The Agent Skills Directory

[SAFE]: The analysis did not reveal any malicious patterns. The skill follows secure coding practices, such as implementing HTML escaping for user-supplied content and providing detailed logging for auditability.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data in the form of .pptx files within scripts/convert_pptx_to_html_v2.py.
Ingestion points: PowerPoint XML structures (text, metadata, and slide content) read from provided .pptx files.
Boundary markers: Absent. The skill does not explicitly use delimiters when the agent reads the generated conversion reports or logs.
Capability inventory: The skill writes generated HTML, CSS, and JS files to the local filesystem and extracts media assets. It also generates JavaScript code for animation and chart rendering.
Sanitization: The skill uses an _escape_html method in scripts/convert_pptx_to_html_v2.py and scripts/smartart_parser.py to sanitize text content before it is placed into the generated HTML output, mitigating XSS and basic injection risks.
[EXTERNAL_DOWNLOADS]: The generated HTML output references the Chart.js library from the cdn.jsdelivr.net Content Delivery Network. This is a well-known and legitimate service used according to its intended purpose for the tool's chart-rendering features.
[EXTERNAL_DOWNLOADS]: The skill requires several standard Python packages (python-pptx, openpyxl, fonttools) from the official PyPI registry, which are necessary for the tool's core functionality.

pptx-to-html