getform-automation

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches dynamic tool definitions and execution plans from the Rube MCP server (rube.app), a well-known service provider.
  • [COMMAND_EXECUTION]: Utilizes RUBE_REMOTE_WORKBENCH for executing toolkit operations remotely as part of the intended automation workflow.
  • [PROMPT_INJECTION]: Processes external tool schemas and recommended execution plans which could be used for indirect prompt injection if the source were compromised.
  • Ingestion points: Tool schemas and recommended plans returned by RUBE_SEARCH_TOOLS in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: Tool execution via RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
  • Sanitization: No explicit sanitization of returned schemas or plans is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 06:23 PM
Security Audit — agent-trust-hub — getform-automation