design-a-chart
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill exclusively utilizes vendor-owned resources and references official documentation.- [INDIRECT_PROMPT_INJECTION]: The skill ingests user stories and data requirements to generate chart configurations, representing a standard input surface for data visualization tools.
- Ingestion points: User stories, metric definitions, and explanatory goals provided as natural language requests.
- Boundary markers: The skill uses a structured
ChartBriefinterface inSKILL.mdto scope data, but lacks explicit instructions to sanitize user-provided strings before they are used in generated code. - Capability inventory: The agent is guided to generate
@tanstack/chartsmarks and scales, which are presentation-layer components. - Sanitization: No specific data filtering or escaping mechanisms are described for inputs interpolated into the chart brief or code blocks.
Audit Metadata