ppt-html-authoring
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied 'key content' from outline entries and incorporates it directly into HTML templates, creating an attack surface for indirect prompt injection.
- Ingestion points: Processes 'outline entry' and 'key content' as defined in the Workflow section of SKILL.md.
- Boundary markers: Absent; there are no instructions to use delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The generated slide.html files include JavaScript capabilities (e.g., Chart.js) and are rendered using Playwright (slide_screenshot), which executes the resulting code.
- Sanitization: Absent; the instructions do not require the agent to sanitize or escape user-provided content before interpolation into the HTML output.
- [EXTERNAL_DOWNLOADS]: The skill references resources from well-known and trusted external services for its core functionality.
- Evidence: The skill instructions and reference files (references/slide-html-rules.md) guide the agent to fetch Chart.js, d3.js, Google Fonts, and icon libraries (Heroicons, Lucide, Feather, Tabler) via HTTPS CDNs such as jsdelivr.net and googleapis.com.
Audit Metadata