web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill fetches content from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. Under the [TRUST-SCOPE-RULE], this is downgraded to LOW becausevercel-labsis a trusted GitHub organization.- [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface by retrieving instructions from an external source to govern agent behavior. Mandatory Evidence Chain (Category 8): 1. Ingestion points:SKILL.md(fetches from remote URL). 2. Boundary markers: Absent in the skill description. 3. Capability inventory: Reads local files and outputs text. 4. Sanitization: Absent. The risk is mitigated by the trusted status of the repository source.
Audit Metadata