frame-flowchart-sticky
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate flowchart nodes, which presents a surface for indirect prompt injection if the user content contains malicious instructions intended for downstream systems.
- Ingestion points: User-provided process/workflow content as described in
SKILL.md("节点文字直接来自用户输入"). - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the interpolated content.
- Capability inventory: Generates HTML and SVG structures that include the user data in
<h3>and<p>tags. - Sanitization: There is no mention of escaping, validation, or sanitizing the user-supplied strings before interpolation.
- [EXTERNAL_DOWNLOADS]: The skill's example template fetches resources from well-known services.
- Fetches the Tailwind CSS framework from
https://cdn.tailwindcss.com. - Fetches hand-drawn style typography from Google Fonts (
https://fonts.googleapis.com).
Audit Metadata