architecture-diagram
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided descriptions of software components and system layers to generate a diagram. While this represents a data ingestion surface, the risk is minimized because the skill instructs the agent to produce only static HTML/SVG and explicitly forbids JavaScript, which prevents cross-site scripting (XSS) or other malicious code execution in the generated output.
- [EXTERNAL_DOWNLOADS]: The skill allows a single external reference to Google Fonts for typography. This is a well-known service and is used here solely for visual styling of the generated diagram, posing no security threat.
Audit Metadata