make-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No directives found to bypass safety constraints or override instructions.
  • [Indirect Prompt Injection] (LOW): The skill ingests external data from the Make API (e.g., operation logs).
  • Ingestion points: Output from MAKE_GET_OPERATIONS.
  • Boundary markers: None specified.
  • Capability inventory: Orchestration via Rube MCP.
  • Sanitization: None mentioned.
  • [Remote Code Execution] (SAFE): No remote scripts are downloaded or executed. The reference to rube.app/mcp is for MCP server configuration and does not involve direct script execution on the host.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:18 AM