ui-design

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands, including curl and Invoke-WebRequest for asset management and grep for code quality auditing.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to download external resources like images and fonts from remote URLs. It provides template commands for these operations and includes security guidance such as avoiding private hosts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied context for design generation, creating a surface for indirect prompt injection without explicit sanitization or input boundaries.
  • Ingestion points: User-provided purpose statements and interface planning requirements in SKILL.md.
  • Boundary markers: None specified for user-provided context.
  • Capability inventory: Shell execution (curl, grep) and file system write operations.
  • Sanitization: No methods for sanitizing or escaping user input are documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 05:01 AM