21st-registry
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of component source code and registry metadata from the 21st.dev platform.
- Ingestion points: Code and metadata are fetched via the add and search commands in SKILL.md.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in the downloaded content are provided to the agent.
- Capability inventory: The skill facilitates writing files to the local file system and executing package installation commands (npm/pnpm/yarn/bun add) through the vendor CLI.
- Sanitization: No content sanitization or validation of the downloaded component code is described, though the CLI performs import path mapping.
- [COMMAND_EXECUTION]: The skill uses the @21st-dev/registry CLI to perform operations such as publishing components, searching registries, and managing team settings.
- [EXTERNAL_DOWNLOADS]: Fetches skill configuration and component source code from the vendor's official domain (21st.dev) and associated GitHub repositories.
Audit Metadata