frame-flowchart-sticky

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to take user-provided process content (flowchart steps, titles, and descriptions) and interpolate it directly into an HTML/SVG template.
  • Ingestion points: User content provided via the prompt as specified in the instructions (SKILL.md).
  • Boundary markers: Absent; the template instructions do not provide delimiters or instructions for the agent to separate user-provided data from the structural code.
  • Capability inventory: The skill generates static HTML, CSS, and inline SVG. It does not perform network operations, file writes, or command execution within the generated code.
  • Sanitization: Absent; there are no instructions to sanitize, escape, or validate the user-provided text before it is placed into the HTML tags.
  • [EXTERNAL_DOWNLOADS]: The generated example implementation (example.html) references external resources for styling and typography.
  • The skill fetches the Tailwind CSS framework from cdn.tailwindcss.com.
  • The skill loads handwriting fonts from fonts.googleapis.com (Google Fonts).
  • These are well-known services commonly used for web development and do not represent a security risk in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:00 AM