network-protocol-viz

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The visualization assets (e.g., assets/HTTPS.html, assets/router-routing-table.html) reference styling and graphing libraries from well-known technology services.
  • Evidence: References to https://cdn.tailwindcss.com, https://cdn.jsdelivr.net/npm/font-awesome@4.7.0/css/font-awesome.min.css, and https://cdn.jsdelivr.net/npm/chart.js@4.4.8/dist/chart.umd.min.js.
  • [PROMPT_INJECTION]: The skill architecture allows for potential indirect prompt injection by accepting user-provided protocol names and descriptions to generate executable HTML/JavaScript code.
  • Ingestion points: Prompt template variables such as {协议名称} and {简短描述} in references/prompts.md.
  • Boundary markers: Absent from the reference prompts.
  • Capability inventory: Generates single-file HTML/JavaScript code (e.g., logic defined in SKILL.md Step 3).
  • Sanitization: No explicit sanitization or escaping instructions are provided for user-supplied data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 03:57 AM
Security Audit — agent-trust-hub — network-protocol-viz