data-viz-2025

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of documentation, utility TypeScript scripts for data processing, and React component examples. Analysis found no evidence of malicious intent, data exfiltration, or obfuscation.\n- [EXTERNAL_DOWNLOADS]: The skill recommends several well-known and trusted visualization libraries (Recharts, D3.js, Nivo, Visx, Observable Plot) and testing tools (Percy, Chromatic) available through official package registries.\n- [COMMAND_EXECUTION]: The documentation provides standard shell commands for development workflows, including package installation via npm and running visual regression tests with Percy.\n- [PROMPT_INJECTION]: Provides architectural patterns for 'AI-Enhanced Visualizations' where data is passed to an LLM to generate insights. This represents an indirect prompt injection surface if untrusted data is processed without sufficient boundary markers or sanitization.\n
  • Ingestion points: SKILL.md and references/data-storytelling.md (AI Annotation feature description)\n
  • Boundary markers: Not explicitly defined in the provided architectural examples\n
  • Capability inventory: Use of fetch to send data to external APIs for insight generation\n
  • Sanitization: No explicit sanitization or input validation logic is shown in the AI-annotation code snippets
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:19 PM