ux-writing
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the Figma Model Context Protocol (MCP) server from a remote URL (
https://mcp.figma.com/mcp). This refers to a well-known professional design service and is used to extend the agent's capabilities to interact with design files. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow where the agent ingests and analyzes text strings from external Figma designs. This represents an attack surface for indirect prompt injection if the design content contains malicious instructions intended to influence the agent's behavior.
- Ingestion points: Text elements and design nodes extracted from Figma files via the Figma MCP server (described in
docs/figma-integration.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat external content as untrusted data.
- Capability inventory: The skill provides frameworks for auditing and generating text; it does not include active scripts, file-writing, or network-sending capabilities beyond the Figma integration.
- Sanitization: There are no instructions or patterns provided for sanitizing or filtering input received from external design files.
Audit Metadata