figma-design-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is well-scoped and adheres to the principle of least privilege. It explicitly restricts its operations to local file reading and writing within a designated output directory (./figma-output/).
- [SAFE]: The skill includes explicit guardrails preventing it from making external network requests to Figma or other services, mitigating data exfiltration risks.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external JSON data (Figma node names and labels). However, given the lack of dangerous capabilities (no network access, no shell execution) and the narrow scope of its output (markdown documentation), this is considered a safe operational surface.
- Ingestion points: Local JSON files in ./figma-output/ specified in the SKILL.md file.
- Boundary markers: None identified in the provided instructions.
- Capability inventory: Local file read/write operations; no subprocess calls, execution commands, or network operations detected.
- Sanitization: No explicit sanitization or validation of the input JSON content is performed before interpolation into documentation outputs.
Audit Metadata