xiaoqi-minimalist-slides
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches Reveal.js CSS and JavaScript files from the JSDelivr CDN, a well-known and trusted service for delivering open-source frontend assets. Evidence: The assets/deck-template.html file contains links to https://cdn.jsdelivr.net/npm/reveal.js@6.0.1/
- [COMMAND_EXECUTION]: The skill's workflow involves generating images via external AI tools to serve as visual metaphors for each chapter. This is an integral part of the presentation design process described in the skill instructions.
- [PROMPT_INJECTION]: The skill processes user-supplied content to populate an HTML presentation template, representing a typical surface for indirect prompt injection. 1. Ingestion points: The agent ingests user content to organize into slides (SKILL.md). 2. Boundary markers: No specific delimiters or safety warnings are included in the template interpolation instructions. 3. Capability inventory: The agent has the capability to write local files (index.html) and verify them using browser tools. 4. Sanitization: No explicit content sanitization or escaping mechanisms are described in the instructions.
Audit Metadata