figma-pilot-mcp
Fail
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: HIGHDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill provides a tool named
figma_executedesigned to execute arbitrary JavaScript code at runtime. This allows the AI agent to dynamically generate and run logic against the Figma API, which is a high-risk capability if the agent's instructions are compromised. - [EXTERNAL_DOWNLOADS]: The installation process involves downloading and executing the package
@youware-labs/figma-pilot-mcpfrom the public NPM registry usingnpx. This introduces a dependency on an external third-party source not listed among trusted vendors. - [INDIRECT_PROMPT_INJECTION]: The skill's functionality includes querying Figma documents for content (e.g., node names, text content, and layer data). This data is returned to the agent's context, providing an attack surface where malicious instructions embedded in a design file could influence the agent's behavior.
Recommendations
- AI detected serious security threats
Audit Metadata