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 markdown instructions from a remote repository.
- Evidence: Fetching from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdinSKILL.md. - Trust Status: The
vercel-labsorganization is a trusted source, downgrading this finding from MEDIUM to LOW. - INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to ingest remote content that dictates its operational rules and output format, creating an attack surface.
- Ingestion points: Guidelines fetched from a remote URL in
SKILL.md. - Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands are present.
- Capability inventory: Network access via WebFetch and local file read access to user-specified paths.
- Sanitization: None; the skill is explicitly instructed to 'Apply all rules from the fetched guidelines'.
Audit Metadata