rayden-use
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests design tokens, component specifications, and anatomy data from the external '@raydenui/ai' MCP server or package. If this external source provides malicious content, it could influence the agent's behavior.
- Ingestion points: Component data and tokens are loaded from external sources as described in the 'How It Works' section of SKILL.md.
- Boundary markers: No explicit delimiters or 'ignore' instructions for external data are specified.
- Capability inventory: The skill uses the 'mcp__claude_ai_Figma__use_figma' tool to write to Figma files and 'Read' for local file access.
- Sanitization: There is no mention of sanitizing or validating the structure of the retrieved component data before processing.
- [DYNAMIC_EXECUTION]: The skill generates Figma Plugin API code at runtime to construct UI components. While this is the intended mechanism for Figma automation, it involves the assembly and execution of dynamically generated code logic.
- [EXTERNAL_DOWNLOADS]: The instructions direct the user to install the '@raydenui/ai' package or MCP server to provide the necessary design system data, introducing an external dependency into the workflow.
Audit Metadata