data-visualization
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external, untrusted data to generate visual artifacts and executable code (HTML/JavaScript and Python).
- Ingestion points: The skill is designed to ingest and process user data (referenced in various modules) to determine chart types and populate visualizations.
- Boundary markers: The instructions lack specific guidance on using delimiters or "ignore embedded instructions" warnings when processing data that might contain malicious natural language instructions.
- Capability inventory: The skill leverages capabilities to generate self-contained HTML files (using Chart.js via CDN), Canvas-based visuals, and Python code (using Plotly or Matplotlib).
- Sanitization: There are no explicit instructions for the agent to sanitize, escape, or validate external content before interpolating it into the generated visualization code or prompts.
Audit Metadata