shadcn-components
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the user codebase and external component registries, which is then used to perform file write and edit operations.\n
- Ingestion points: Project source code (via explore-codebase) and external component registries (via mcp__shadcn MCP tools).\n
- Boundary markers: Instructions do not specify delimiters or warnings to ignore instructions that might be embedded in existing code or registry data.\n
- Capability inventory: The skill has permissions to Write and Edit files in the user project.\n
- Sanitization: No mechanisms are defined for sanitizing or validating ingested code before it is used in code generation tasks.\n- [SAFE]: The skill utilizes industry-standard libraries (Radix UI, Base UI) and follows established architecture patterns for UI component development. All external resource references trace back to official documentation or vendor-associated MCP tools.
Audit Metadata