infographic-structure-creator
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill's instructions or logic.
- [COMMAND_EXECUTION]: The skill instructions specify scanning the local
src/designs/structuresdirectory. This is a legitimate operation intended to help the agent maintain consistency with existing code patterns in the user's repository. - [PROMPT_INJECTION]: The skill generates code based on user-specified requirements, which inherently creates a surface for indirect prompt injection (Category 8). This is addressed by a strict framework that limits output to a predefined whitelist of JSX components and utilities. Evidence Chain: 1. Ingestion: User-provided infographic layout requirements. 2. Boundary markers: Comprehensive rules and constraints defined in
references/structure-prompt.md. 3. Capability: Ability to scan local structure files and generate TypeScript code. 4. Sanitization: The framework restricts generation to a specific set of safe atomic and layout components. - [EXTERNAL_DOWNLOADS]: The reference documentation mentions support for
d3,lodash-es, andtinycolor2. These are standard, widely-trusted industry libraries for data visualization and utility functions.
Audit Metadata