card-xiaohongshu
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references assets from well-known services, including the Tailwind CSS CDN (
cdn.tailwindcss.com) and Google Fonts (fonts.googleapis.com). It also points to the author's repository on GitHub (nexu-io/html-anything) for project context. These are standard resources for web-based card generation. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content to populate the HTML card templates. While this technically creates a surface where malicious user text could attempt to influence the agent's generation, the skill lacks high-privilege capabilities—such as file system access or network exfiltration—that would make such an injection actionable.
- Ingestion points: User content is ingested to fill the template structure defined in
SKILL.md. - Boundary markers: The template uses a clear structural outline (Cover, Body, Summary) to separate and organize user data.
- Capability inventory: The skill is strictly limited to generating visual HTML previews and does not execute system commands or perform network operations.
- Sanitization: The skill relies on the underlying AI agent's native safety filters to handle potentially malicious output.
Audit Metadata