figma-design-handoff
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from external sources, creating a potential vector for indirect prompt injection. \n
- Ingestion points: Data enters the agent's context through the Figma REST API (api.figma.com), the Figma Dev Mode MCP Server (tools like
get_design_context), and theWebFetchtool used for design documentation. \n - Boundary markers: The prompt instructions do not include specific delimiters or 'ignore' directives to prevent the agent from following malicious instructions potentially embedded in Figma component names, descriptions, or web content. \n
- Capability inventory: The skill possesses significant capabilities, including local file system interaction (
Read,Glob,Grep), network access (WebFetch,WebSearch), and tool-based interactions with external design canvases. \n - Sanitization: There is no evidence of explicit sanitization or validation logic applied to the external content before it is processed by the agent.
Audit Metadata