data-report
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill loads Tailwind CSS and Chart.js libraries from official, well-known content delivery networks (jsdelivr and tailwindcss.com). These resources are standard for web-based data visualization and are used as intended for the skill's primary functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data provided by users (CSV, Excel, JSON) to generate reports, which is a standard data ingestion surface.
- Ingestion points: User-supplied data files processed during the report generation phase as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters for separating user data from agent instructions.
- Capability inventory: The skill is limited to generating HTML and JavaScript for browser-based rendering; it lacks capabilities for network exfiltration, local file modification, or subprocess execution.
- Sanitization: The template relies on the agent's internal logic to parse and display data without providing explicit sanitization rules.
Audit Metadata