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/clipackage, which is the official command-line interface for the Membrane platform (provided by the author 'membranedev'). - [COMMAND_EXECUTION]: Documentation provides instructions for using the
membraneCLI 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-fileandget-comments). 2. Boundary markers: Not specified. 3. Capability inventory: Execution of actions and proxy requests via themembraneCLI. 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