skills/starc007/ui-components/beui/Gen Agent Trust Hub

beui

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a component registry from https://beui.dev/r/registry.json at runtime to determine available components.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx, pnpm, or bun to add remote components to the local project (e.g., npx shadcn@latest add @beui/<slug>).
  • [INDIRECT_PROMPT_INJECTION]:
    • Ingestion points: Fetches external data from https://beui.dev/r/registry.json (SKILL.md).
    • Boundary markers: None. The agent is instructed to use the remote registry as the 'source of truth' without boundary delimiters for the JSON content.
    • Capability inventory: Execution of system commands through package managers (npx, pnpm, bunx) and file system access as part of the shadcn installation process.
    • Sanitization: The skill lacks validation or sanitization mechanisms for the data retrieved from the remote registry before using it to construct shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 08:16 PM
Security Audit — agent-trust-hub — beui