architecture-diagram
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's HTML template (
templates/template.html) references the Google Fonts API (fonts.googleapis.com) to load the 'JetBrains Mono' typeface. This is a well-known service and the reference is for legitimate design purposes. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided architecture descriptions to generate HTML and SVG graphics, presenting a vulnerability surface for indirect prompt injection.
- Ingestion points: System architecture descriptions provided by the user during the skill's workflow (SKILL.md).
- Boundary markers: No specific delimiters or 'ignore' instructions are provided to the agent for isolating user content within the HTML template.
- Capability inventory: The skill utilizes the
write_filetool to save the generated HTML file to the user's local disk (SKILL.md). - Sanitization: There are no instructions for sanitizing or escaping user-provided labels or annotations before they are embedded into the HTML document, which could allow for script injection if the input is malicious.
Audit Metadata