verify-figma-mcp-transports

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local repository scripts and build tasks using the bun runtime, such as bun packages/mcp/scripts/probe-transports.ts and bun packages/mcp/bin/index.mjs socket. These commands are scoped to the project's internal directory structure and are intended for transport debugging.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its interaction with external data sources.
  • Ingestion points: Content is ingested from Figma's REST API and WebSocket transports during the transport comparison phases (Phase 1 and 4).
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the data being compared.
  • Capability inventory: The agent has access to shell execution via bun and user interaction via AskUserQuestion while processing these inputs.
  • Sanitization: No sanitization or schema validation is described for the payloads received from the Figma APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 08:31 AM
Security Audit — agent-trust-hub — verify-figma-mcp-transports