web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: References UI guidelines from Vercel Labs' official GitHub repository.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes untrusted content from user-specified files to perform its audit.
- Ingestion points: Files provided via the
$ARGUMENTSvariable incommand.mdand referenced inSKILL.md. - Boundary markers: Absent. There are no explicit instructions or delimiters used to separate the rules from the potentially adversarial content in the audited files.
- Capability inventory: The skill utilizes file reading and text output capabilities.
- Sanitization: Absent. Content from audited files is interpolated into the agent's context without filtering or escaping.
Audit Metadata