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.jsonat runtime to determine available components. - [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
npx,pnpm, orbunto 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 theshadcninstallation process. - Sanitization: The skill lacks validation or sanitization mechanisms for the data retrieved from the remote registry before using it to construct shell commands.
- Ingestion points: Fetches external data from
Audit Metadata