pptx
Use this skill any time the user wants to create a new PowerPoint presentation, slide deck, pitch deck, or .pptx file from scratch. Covers creating business presentations, quarterly reports, project proposals, product roadmaps, training materials, and any multi-slide document destined for PowerPoint. Works by generating HTML/CSS slides (which LLMs excel at), rendering them in agent-browser for pixel-accurate DOM position extraction, and assembling the final PPTX with native PowerPoint charts, tables, and images via PptxGenJS. Includes bundled scripts for validation, DOM extraction, and PPTX assembly. Do NOT use this skill for editing existing PPTX files, converting other formats to PPTX, or extracting content from PPTX files.
95
100%
Does it follow best practices?
Impact
76%
2.05xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.80). The skill explicitly injects and executes third‑party code and media: SKILL.md and references/pptxgenjs.md instruct the agent-browser to load Chart.js from https://cdn.jsdelivr.net/... (render-placeholders.js) and both render-placeholders.js and build-pptx.js fetch and render arbitrary external image URLs (e.g., images.unsplash.com) provided in placeholder data, so untrusted web content is fetched, executed/parsed, and incorporated into the DOM/extraction and final PPTX build and therefore could influence agent behavior.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.70). The skill injects and executes remote JavaScript at runtime from https://cdn.jsdelivr.net/npm/chart.js@4.4.1/dist/chart.umd.min.js via agent-browser eval (document.createElement('script'); s.src=...), which runs fetched code in the rendering environment and is required for rendering chart placeholders in the preview step.
- Repository
- treasure-data/td-skills
- Commit
79bb9b8
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.