qt-figma-token-extraction
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for fetching design data from the official Figma API (api.figma.com). This is a well-known service, and the operations are limited to reading design variables and styles required for the skill's primary function.
- [COMMAND_EXECUTION]: The skill provides curl commands for the user to execute manually in their terminal. These commands are used to export JSON data from Figma when the MCP method is not preferred. The agent does not execute these commands autonomously.
- [INDIRECT_PROMPT_INJECTION]: The skill processes JSON data exported from Figma to generate QML code, creating a potential surface for indirect injection if the source Figma file contains malicious content. 1. Ingestion points: design-tokens-raw.json and text-styles-nodes.json in the root directory. 2. Capability inventory: The skill has the capability to write multiple .qml files, design-tokens.json, and modify CMakeLists.txt and main.cpp. 3. Boundary markers: No explicit boundary markers or 'ignore' instructions are provided for the data processing step. 4. Sanitization: The skill applies type mapping and naming conventions (snake_case) to the ingested data, which serves as a basic validation layer.
Audit Metadata