figma-integration
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes processes that ingest data from external Figma files, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill utilizes
figma.currentPage.selectionandfigma.variables.getLocalVariableCollections()inSKILL.mdto extract selection data and design variables from the Figma environment. - Boundary markers: The instructions and provided code snippets do not include boundary markers or warnings to disregard instructions that might be embedded in design metadata.
- Capability inventory: The skill includes code snippets in
SKILL.mdthat usefs.writeFileSyncto write data to the local filesystem. - Sanitization: There is no evidence of sanitization or validation of the extracted design data (such as variable names or descriptions) before it is used or written to files.
Audit Metadata