figma

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the @membranehq/cli package, which is the official command-line interface for the Membrane platform (provided by the author 'membranedev').
  • [COMMAND_EXECUTION]: Documentation provides instructions for using the membrane CLI to search for connectors, establish connections, and run actions against the Figma API.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from Figma, presenting a surface for indirect prompt injection. 1. Ingestion points: File metadata, variables, and comments (e.g., via get-file and get-comments). 2. Boundary markers: Not specified. 3. Capability inventory: Execution of actions and proxy requests via the membrane CLI. 4. Sanitization: Not explicitly documented. This surface is inherent to the integration's purpose and is handled within the context of the user's authenticated session.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 02:18 PM