web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from the Vercel Labs official GitHub repository (raw.githubusercontent.com/vercel-labs/web-interface-guidelines). This is a standard functional requirement for the skill to retrieve its rule set from a reputable source.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from both local files and a remote markdown file, creating an indirect prompt injection surface.
  • Ingestion points: The agent reads user-provided files and content from the guidelines URL.
  • Boundary markers: No explicit delimiters or instructions to disregard embedded instructions are present in the skill.
  • Capability inventory: The skill is limited to file reading and text output; it does not have access to tools for command execution, network exfiltration, or persistent file system changes.
  • Sanitization: There is no evidence of filtering or validation for the content retrieved from external sources or local files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 12:43 AM
Security Audit — agent-trust-hub — web-design-guidelines