web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- EXTERNAL_DOWNLOADS (LOW): The skill fetches guidelines from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. Although it downloads remote content, the source organizationvercel-labsis a Trusted External Source, justifying a LOW severity. - PROMPT_INJECTION (LOW): The skill exhibits an attack surface for indirect prompt injection (Category 8) by fetching runtime instructions from a remote source. * Ingestion points:
command.mdfile from GitHub. * Boundary markers: Absent; there are no clear delimiters to prevent the remote content from overriding core system instructions. * Capability inventory: Reading local files (UI code). * Sanitization: Absent; the skill does not specify any validation or filtering of the fetched content.
Audit Metadata