shadcn-component-review
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied code snippets for UI components, creating a surface where malicious instructions could be embedded in code comments or data attributes.
- Ingestion points: User-provided component code or layout snippets (SKILL.md).
- Boundary markers: None present.
- Capability inventory: Uses grep for static analysis and npx shadcn for metadata retrieval; no high-risk capabilities like file writes or arbitrary network exfiltration.
- Sanitization: None present.
- [COMMAND_EXECUTION]: Executes the shadcn CLI tool to gather project context and documentation.
- Evidence: npx shadcn@latest info --json and npx shadcn@latest docs are used to verify project styles and primitive versions.
- [EXTERNAL_DOWNLOADS]: Fetches project-specific information and documentation through the official shadcn utility.
- Evidence: Uses npx shadcn@latest to pull configuration and component documentation from the official shadcn registry.
Audit Metadata