Skills
skills/0xkynz/codekit/shadcn-ui/Gen Agent Trust Hub

shadcn-ui

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npx to execute shadcn@latest commands for initializing projects and adding UI components.\n- [EXTERNAL_DOWNLOADS]: Fetches the shadcn CLI tool and UI component code from the official npm registry.\n- [PROMPT_INJECTION]: The skill lacks input validation for component names, creating a surface for indirect prompt injection.\n
  • Ingestion points: User-provided component names or lists used in the add workflow in SKILL.md.\n
  • Boundary markers: No delimiters or "ignore instructions" warnings are used to separate input from the command template.\n
  • Capability inventory: The skill enables shell execution via npx as its primary mechanism for adding components.\n
  • Sanitization: Input parameters are interpolated directly into shell commands without escaping or validation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:06 PM