build-daisyui-mcp

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

• Third-party content exposure detected (high risk: 0.90). The skill's mandatory Figma workflow (see "Workflow — Figma to daisyUI" in SKILL.md) requires calling daisyui-blueprint-Figma-to-daisyUI with a Figma URL to FETCH and ANALYZE a Figma node tree—clearly ingesting untrusted, user-generated third-party content that the agent must interpret and which drives snippet selection and build decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's MCP setup instructs running remote code at runtime via "npx -y daisyui-blueprint@latest" (appearing in the VS Code MCP config and Claude MCP examples), which will fetch and execute a remote package that the skill relies on for snippet/Figma tools, so this is a runtime external dependency that can execute code and influence agent behavior.