shadcn
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONDYNAMIC_CONTEXT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to run
npx shadcn@latest, which downloads and executes code from the npm registry. This is the primary method for adding components and initializing projects. - [DYNAMIC_CONTEXT_INJECTION]: A shell command is executed when the skill is loaded to provide the agent with project context. Evidence:
!npx shadcn@latest info --jsoninSKILL.md. - [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch documentation and examples from
ui.shadcn.comandraw.githubusercontent.com(a whitelisted domain). - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external documentation and community registries. Ingestion points: documentation URLs and community registry files referenced in
SKILL.mdandcli.md. Boundary markers: none identified for the fetched external content. Capability inventory: shell execution via npx and file system writes via CLI. Sanitization: relies on the shadcn CLI for project modifications.
Audit Metadata