scrollytelling-and-parallax-data-visualization
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill consists entirely of instructional text and design workflows aimed at creating data visualizations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data and story contexts to generate visualizations and design concepts. While this represents a standard attack surface for indirect prompt injection, the instructions emphasize analytical integrity and evidence preservation.
- Ingestion points: User-provided story takeaways, existing page descriptions, and fictional data simulation parameters (found in
references/foundations/meaning-preserving-visual-design-workflow.mdandreferences/foundations/fictional-data-story-simulation.md). - Boundary markers: The skill does not explicitly define unique delimiters for untrusted data, though it mandates a 'Evidence Lock' and 'Semantic Design Contract' to maintain claim fidelity.
- Capability inventory: The skill is capable of generating implementation code (D3, React, GSAP) and prompts for image generation tools.
- Sanitization: The workflow includes human-in-the-loop 'Approval Gates' and 'Semantic Fidelity QA' which serve as manual verification points against unexpected outputs.
Audit Metadata