slideshow

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • Command Execution: The skill utilizes npx commands to manage skill updates, search for visual assets in the HyperFrames catalog, and validate project integrity. These commands are standard operations within the HyperFrames development environment.
  • External Downloads: The skill includes a reference to the Three.js library hosted on cdn.jsdelivr.net, which is a widely recognized and well-known content delivery network for web development resources.
  • Indirect Prompt Injection: The skill features functionality to port content from external web pages and Figma URLs into slideshow compositions. This involves processing untrusted external data, which is a common pattern for conversion tools. The skill documentation explicitly mentions using specific tools for SVG sanitization and provenance tracking when importing these assets.
  • Dynamic Execution: The skill generates and implements JavaScript for complex behaviors, including slide visibility logic, interactive media synchronization using the BroadcastChannel API, and 3D rendering via Three.js. It also utilizes localStorage for managing presenter notes locally within the browser.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 05:18 AM