NYC

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 content from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md'. According to the [TRUST-SCOPE-RULE], this finding is downgraded to LOW because 'vercel-labs' is a trusted GitHub organization.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) as it processes external instructions. 1. Ingestion points: Remote markdown file (command.md) fetched via WebFetch. 2. Boundary markers: None present in the instruction set to isolate the fetched rules. 3. Capability inventory: Skill can read local UI code files. 4. Sanitization: No sanitization of the fetched instruction set is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:52 PM