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 dynamic instructions from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md'. Since the source is the 'vercel-labs' organization, which is a Trusted External Source, the finding is downgraded to LOW per the TRUST-SCOPE-RULE.
- Indirect Prompt Injection (LOW): The skill possesses an attack surface for indirect injection as it processes both remote and local content. 1. Ingestion points: Fetching 'command.md' and reading local user UI files. 2. Boundary markers: Absent; there are no specific delimiters defined to isolate external instructions from data. 3. Capability inventory: Limited to reading local files and outputting text. 4. Sanitization: Absent; the skill does not perform validation or escaping on the ingested data before using it to apply rules.
Audit Metadata