d3-visualization
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions encourage the user to download and install code from a third-party GitHub repository (https://github.com/jiannanya/snow-d3.git) to provide visualization assets and scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided datasets to generate complex visualizations, which introduces an attack surface for indirect instructions.
- Ingestion points: The skill ingests untrusted external data such as "sales data" or "custom datasets" provided by the user for visualization tasks (SKILL.md).
- Boundary markers: None identified. The skill does not provide specific instructions to the agent to ignore instructions embedded within the data provided for charts.
- Capability inventory: The skill facilitates the generation of D3.js visualization code. It does not contain internal scripts with file-writing or network capabilities.
- Sanitization: No evidence of data sanitization, validation, or escaping logic is provided in the documentation.
Audit Metadata