card-xiaohongshu
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references Tailwind CSS via
cdn.tailwindcss.comand Google Fonts viafonts.googleapis.comin theexample.htmlfile. These are established, well-known services used for UI styling and are documented here as standard external dependencies. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a template engine that ingests untrusted user content to generate HTML cards, presenting a surface for potential injection.
- Ingestion points: User-supplied text and data are processed through the
example_promptand instruction set inSKILL.mdto populate theindex.htmlpreview. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying instructions embedded within the user's content during the card generation process.
- Capability inventory: The skill is designed for visual output generation (HTML/CSS/Preview); it does not contain code for file system modification, network exfiltration, or command execution.
- Sanitization: There are no explicit instructions or scripts for sanitizing, escaping, or validating the input data before it is interpolated into the HTML structure.
Audit Metadata