web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from Vercel's official GitHub repository at runtime.
  • [PROMPT_INJECTION]: The skill processes untrusted user data which presents a surface for indirect prompt injection.
  • Ingestion points: User-specified files and the external guidelines markdown file.
  • Boundary markers: No explicit delimiters or instructions are used to isolate the data being audited from the agent's core processing logic.
  • Capability inventory: The skill is restricted to file reading and text output; no capabilities for subprocess execution, persistent file writing, or unauthorized network operations were identified.
  • Sanitization: Content from the audited files is processed directly without filtering for malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:42 AM