carousel-post-images
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a professional content creation workflow. It uses standard Node.js libraries (Playwright) for rendering tasks and provides clear instructions for manual review via an audit harness.
- [COMMAND_EXECUTION]: The skill uses scripts (
render-carousel.mjsandaudit-carousel.mjs) to automate the rendering and auditing process. These scripts interact with the local file system to read deck plans (slides.html) and write output assets (PNG,prompts.md,carousel-audit.md). All operations are scoped to the project directory. - [EXTERNAL_DOWNLOADS]: The
slides.htmltemplate fetches fonts from Google's official font CDN (fonts.googleapis.comandfonts.gstatic.com). This is standard practice for web-based rendering and follows the trusted source rules. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics to generate carousels. It includes an 'Audit Stage' (Stage 6) specifically designed to catch errors, garbled text, or safety violations before delivery, serving as a robust boundary against potential injection through input data.
- [METADATA_POISONING]: The YAML frontmatter and file descriptions accurately reflect the skill's capabilities and intended use case.
Audit Metadata