figma-design-handoff
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from well-known services, specifically the Figma REST API (api.figma.com) and Applitools (applitools.com), for design token extraction and visual regression testing.
- [COMMAND_EXECUTION]: The workflow incorporates the execution of standard build and testing tools including Node.js scripts, Style Dictionary, Playwright, and the Applitools CLI to automate the conversion of design assets into code.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external sources.
- Ingestion points: Data is ingested via the Figma REST API and local
tokens/figma-raw.jsonfiles. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands were identified in the provided configuration examples.
- Capability inventory: The agent has the capability to execute subprocesses (e.g.,
node,npx) for token transformation and to perform network requests viaWebFetch. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from the design files before it is processed by the transformation scripts.
Audit Metadata