stitch-shadcn-ui

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.72). The skill’s runtime workflow can invoke shadcn MCP actions like list_components / get_component / get_block to fetch component/block source code from shadcn’s (public/community) registry, which is then ingested as readable TSX/text into the agent context for generation/integration—an outsider-authored free-text/code source.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)