web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the latest web interface guidelines from Vercel Labs' official GitHub repository to ensure the audit uses current standards.
- Evidence: References
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests content from an external URL which could influence the agent's behavior during the audit process. However, this content is fetched from a trusted organization's repository.
- Ingestion Point: Step 2 in
SKILL.mdinstructs the agent to read rules from the remote GitHub URL. - Boundary Markers: No explicit delimiters or instructions are provided to the agent to treat the remote content strictly as data.
- Capability Inventory: The skill performs file inspection, reports findings, and may suggest code remediation.
- Sanitization: There is no evidence of sanitization or validation of the fetched content before it is processed.
Audit Metadata