architecture-diagram

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The diagram template (resources/template.html) references the html2canvas and jsPDF libraries from cdn.jsdelivr.net to enable diagram export features. These references include Subresource Integrity (SRI) hashes, which is a security best practice to ensure the downloaded scripts have not been modified.
  • [INDIRECT_PROMPT_INJECTION]: The skill allows for the generation of HTML artifacts based on user-supplied architecture descriptions, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided system names, component labels, and metadata described in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in user data.
  • Capability inventory: Generation of HTML files based on the template provided in resources/template.html.
  • Sanitization: No explicit requirements for sanitizing or escaping user-provided text are mentioned in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:20 AM