web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves design guidelines and formatting instructions from Vercel Labs' official GitHub repository at
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. This reference targets a well-known and trusted service provider. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into its system instructions at runtime, creating an attack surface for indirect prompt injection.
- Ingestion points: Fresh guidelines are fetched from a remote URL via
WebFetchduring every review request. - Boundary markers: The skill does not provide explicit delimiters or instructions to the agent to treat the fetched content as data rather than instructions.
- Capability inventory: The agent has permissions to read local files provided by the user to perform the review.
- Sanitization: The fetched content is applied directly to the agent's context without validation or sanitization.
- [NO_CODE]: The skill is composed entirely of natural language instructions and metadata; it does not distribute or execute custom scripts, binaries, or third-party packages.
Audit Metadata