html-ppt

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides utility shell scripts (scripts/new-deck.sh and scripts/render.sh). Specifically, render.sh executes Google Chrome in headless mode with parameters like --no-sandbox to capture slide screenshots. These are local developer tools for the skill's primary purpose.
  • [EXTERNAL_DOWNLOADS]: The templates fetch various front-end resources from well-known and established services. This includes fonts from Google Fonts (fonts.googleapis.com) and JavaScript libraries from jsDelivr (cdn.jsdelivr.net) and Unpkg (unpkg.com).
  • [DYNAMIC_EXECUTION]: The FX runtime (assets/animations/fx-runtime.js) dynamically loads and executes JavaScript animation modules from the local assets/animations/fx/ directory by injecting script tags into the document.
  • [PROMPT_INJECTION]: The skill instructions in SKILL.md contain strict authoring guidelines (e.g., "NEVER put presenter-only text on the slide itself") intended to ensure high-quality output. These are functional constraints rather than attempts to override agent safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 02:27 PM
Security Audit — agent-trust-hub — html-ppt