web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches configuration and guidelines from Vercel Labs' official GitHub repository.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from both external URLs and user-provided files without adequate protection.
- Ingestion points: Content is retrieved from a remote markdown file and local files specified by the user.
- Boundary markers: No delimiters or protective instructions are used to separate user data from the agent's core instructions.
- Capability inventory: The skill utilizes file reading capabilities and the 'WebFetch' tool to retrieve remote data.
- Sanitization: No evidence of input validation, content escaping, or sanitization is present in the instructions.
Audit Metadata