web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches design guidelines and instructions from Vercel Labs' official GitHub repository. This is a well-known, trusted source used to provide the review rules for the skill's core functionality.\n- [PROMPT_INJECTION]: The skill ingests external data from remote guidelines and user-specified local files, creating a surface for indirect prompt injection. This behavior is necessary for the skill's intended purpose of code auditing.\n
- Ingestion points: Guidelines from the Vercel Labs GitHub repository and local user files provided as arguments.\n
- Boundary markers: No specific delimiters or safety warnings are defined in the skill instructions to separate untrusted data from the agent's instructions.\n
- Capability inventory: Reading local files and performing network fetches via WebFetch.\n
- Sanitization: No explicit sanitization or validation of the fetched or read content is implemented.
Audit Metadata