figma-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to retrieve and process data from external Figma files and comments.
  • Ingestion points: Untrusted data enters the agent's context through tools like FIGMA_GET_FILE_JSON, FIGMA_GET_COMMENTS_IN_A_FILE, and FIGMA_GET_FILE_NODES.
  • Boundary markers: The documentation does not define or use specific boundary markers or delimiters to isolate data retrieved from Figma from the agent's core instructions.
  • Capability inventory: The skill allows the agent to perform actions such as FIGMA_ADD_A_COMMENT_TO_A_FILE and FIGMA_RENDER_IMAGES_OF_FILE_NODES based on the processed data.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the content retrieved from Figma before it is processed by the AI agent.
  • [NO_CODE]: The skill does not contain any Python scripts, Node.js code, or binary executables. It consists entirely of markdown instructions and metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:56 AM