figma
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to run
curlandjqcommands for API interaction. These commands are formatted to retrieve structured design data and are used appropriately for the skill's stated purpose. - [EXTERNAL_DOWNLOADS]: Communicates with the official Figma API (
api.figma.com) to download design information and temporary CDN links for image assets. Figma is a well-known service, and the data retrieved is restricted to design content. - [CREDENTIALS_UNSAFE]: Appropriately manages authentication by referencing an environment variable
$FIGMA_TOKENrather than hardcoding secrets, which is consistent with secure development practices. - [PROMPT_INJECTION]: As the skill ingests external data such as Figma comments and node names, it presents an indirect prompt injection surface. This is a standard operational risk for tools that process user-generated content from external platforms and is mitigated by the agent's internal safety filters.
Audit Metadata