web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches fresh design guidelines from Vercel Labs' official GitHub repository (
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) before performing reviews. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow rules from an external document, creating a potential surface for indirect prompt injection if the source were compromised.
- Ingestion points: The
command.mdfile fetched at runtime inSKILL.md. - Boundary markers: Absent; the skill is instructed to apply all rules from the fetched content without explicit delimiters.
- Capability inventory: Reading local files and writing text output (terse
file:lineformat). - Sanitization: None; the skill directly adopts instructions from the remote resource.
Audit Metadata