web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines and processing instructions from Vercel Labs' official GitHub repository.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied files using instructions fetched from an external Markdown file. This creates a vulnerability where instructions in the fetched file could override intended behavior.
- Ingestion points: Fetches
command.mdfrom GitHub to define review rules (SKILL.md). - Boundary markers: None identified. The skill is instructed to directly apply all rules from the fetched content.
- Capability inventory: The skill reads local files and outputs formatted findings based on the remote rules.
- Sanitization: No validation or sanitization is performed on the fetched remote content before it is used to guide the agent's logic.
Audit Metadata