figma-integration

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill is purely instructional.
  • [NO_CODE] (SAFE): The skill provides guidelines and example code snippets for documentation purposes but does not include functional scripts or automated installation routines.
  • [CREDENTIALS_UNSAFE] (SAFE): The instructions mention the requirement for Figma access tokens but do not contain any hardcoded secrets or placeholders for sensitive keys.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill describes a workflow that ingests external data from the Figma API (e.g., node names, layer content). This represents a theoretical attack surface where malicious instructions in a Figma file could attempt to influence the agent.
  • Ingestion points: Figma API calls (getFile, getNode) described in the guidelines.
  • Boundary markers: Absent in the provided implementation examples.
  • Capability inventory: The described tools have the capability to read design data and export assets to the local filesystem.
  • Sanitization: No sanitization or validation of design data is mentioned in the implementation guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:28 PM