network-protocol-viz
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The generated HTML visualizations fetch CSS and JavaScript libraries from well-known services, including tailwindcss.com and jsdelivr.net. These are used for layout, iconography, and interactive charts.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided protocol names and descriptions to create custom HTML pages. While this constitutes an attack surface where untrusted data is processed, the risk is minimal and inherent to the skill's purpose of code generation.
- Ingestion points: User-provided protocol names and visualization requirements in the agent prompt.
- Boundary markers: None identified in the skill's instructions.
- Capability inventory: The skill produces static HTML files with client-side JavaScript.
- Sanitization: The instructions do not specify sanitization for user-provided labels or descriptions when generating HTML content.
Audit Metadata