rayden-use

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the @raydenui/ai package or MCP server to provide the necessary component data, specs, and design tokens.
  • [COMMAND_EXECUTION]: Generates and executes Figma Plugin API code through the use_figma tool to perform design modifications within Figma files.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its integration with untrusted external data (Figma files).
  • Ingestion points: Processes Figma layer data, component structures, and file metadata retrieved via the use_figma tool and visual data from get_screenshot.
  • Boundary markers: No explicit delimiters or boundary markers (e.g., "ignore embedded instructions") are defined for the data ingested from Figma files.
  • Capability inventory: Includes write access to Figma files (use_figma), screenshot capabilities (get_screenshot), and local file system read access (Read).
  • Sanitization: No documentation exists regarding the sanitization or escaping of data extracted from Figma before it is processed by the agent.
  • [SAFE]: No signs of obfuscation, data exfiltration, or malicious prompt injection targeting the agent's system instructions were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 11:02 PM
Security Audit — agent-trust-hub — rayden-use