NYC
skills/smithery/ai/ui-styling/Gen Agent Trust Hub

ui-styling

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION] (LOW): This skill exhibits a surface for indirect prompt injection as it ingests untrusted design requirements and component names to drive automation tasks.\n
  • Ingestion points: User-provided design requirements and component names processed via scripts/shadcn_add.py and scripts/tailwind_config_gen.py.\n
  • Boundary markers: Absent; no delimiters are defined in the instructions to separate user-provided input from the agent's internal logic.\n
  • Capability inventory: Shell command execution via local Python scripts and file system operations for configuration generation.\n
  • Sanitization: Absent; the skill documentation does not specify validation or escaping for parameters passed to its automation scripts.\n- [COMMAND_EXECUTION] (SAFE): The skill utilizes local Python scripts for legitimate project automation and scaffolding tasks, which is standard for developer-centric skills.\n- [EXTERNAL_DOWNLOADS] (SAFE): Dependencies are fetched from the official npm registry using standard commands (npm, npx) for well-known, reputable packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM