react-dashboard

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions describe building a React component (KPIDashboard) that accepts a data object as a prop. This constitutes an indirect prompt injection surface as the agent will interpolate untrusted data from external sources into the UI components. However, this is the primary intended purpose of the dashboarding skill. \n
  • Ingestion points: The data prop in the KPIDashboard component in SKILL.md. \n
  • Boundary markers: The instructions do not specify any delimiters or safety warnings for the data processed by the React component. \n
  • Capability inventory: The skill utilizes the mcp__tdx-studio__render_react tool to execute and display React code. \n
  • Sanitization: The example code does not demonstrate sanitization or validation of the input data before rendering it in the dashboard.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:50 AM
Security Audit — agent-trust-hub — react-dashboard