code-to-figma

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly includes commands and workflow steps that read components from Figma via the Figma REST API (see the "read --file-key " command) and instruct configuring a Figma MCP to "read tokens/components from Figma files" during SPECIFY/VERIFY, which means the agent will ingest user-generated third‑party content that can influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs installing/running remote packages (e.g., "npx @kylebrodeur/code-to-figma" and cloning https://github.com/kylebrodeur/code-to-figma, and the .mcp.json runs "npx @figma/mcp"), which will fetch and execute external code at runtime and are relied on as required dependencies.