architecture-diagram

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches typography from a well-known service.
  • Evidence: Loads 'JetBrains Mono' font from Google Fonts (fonts.googleapis.com) in the HTML template (templates/template.html).
  • [COMMAND_EXECUTION]: The skill provides instructions for the user to execute shell commands to preview the generated diagrams.
  • Evidence: Recommends using open on macOS and xdg-open on Linux to view the resulting HTML file (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied architecture descriptions to populate text labels within the generated SVG and HTML code, which is a potential surface for injection.
  • Ingestion points: User descriptions of components, connections, and technologies (SKILL.md).
  • Boundary markers: Absent; user strings are interpolated directly into the template.
  • Capability inventory: Uses write_file to save the output locally (SKILL.md).
  • Sanitization: Absent; the skill does not explicitly instruct the agent to escape or sanitize user input before inclusion in the HTML structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:01 PM
Security Audit — agent-trust-hub — architecture-diagram