miro-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard TypeScript examples for Miro board operations, focusing on educational and quick-start purposes.
  • [DATA_EXPOSURE_EXFILTRATION]: The code snippets correctly demonstrate the use of process.env.MIRO_ACCESS_TOKEN for authentication. This follows secret management best practices by avoiding hardcoded credentials.
  • [INDIRECT_PROMPT_INJECTION]: The listBoardItems function ingests data from external Miro boards. While this provides a surface for untrusted content to enter the agent context, the skill handles it safely by only logging the content to the console without performing dangerous follow-up actions like command execution or file writes based on that data.
  • [EXTERNAL_DOWNLOADS]: The skill references the official @mirohq/miro-api package and standard Miro API endpoints (api.miro.com), which are well-known and trusted for this integration context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 11:34 PM
Security Audit — agent-trust-hub — miro-hello-world