qt-figma-component-generation
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes component definitions from Figma via the
get_design_contextMCP tool and uses this data to generate production QML code. This workflow presents an attack surface where a malicious Figma file containing crafted component names or variant properties could potentially influence the agent to generate malicious QML or JavaScript code.\n - Ingestion points: Figma design data is ingested using the
get_design_contexttool inSKILL.md(Step 4).\n - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to treat the Figma-sourced content as untrusted data or to ignore embedded instructions.\n
- Capability inventory: The agent is granted the capability to write multiple
.qmlfiles to the local file system in thecomponents/directory.\n - Sanitization: No explicit sanitization or escaping logic is defined for the Figma-sourced strings before they are interpolated into the generated code templates.
Audit Metadata