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 a markdown file from a remote URL to define its operating logic.
- Evidence: URL
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdis fetched via WebFetch to provide rules. - Trust Note: The organization
vercel-labsis a Trusted GitHub Organization. Per [TRUST-SCOPE-RULE], this finding is downgraded to LOW. - PROMPT_INJECTION (LOW): Risk of Indirect Prompt Injection (Category 8).
- Ingestion points: The remote
command.mdfile is fetched and processed at runtime (SKILL.md). - Boundary markers: Absent. The agent is instructed to 'Apply all rules' and 'follow output format instructions' contained within the external file.
- Capability inventory: The skill reads local files and performs network fetches.
- Sanitization: Absent. The agent adopts instructions from the remote source as its own internal logic.
Audit Metadata