ip2whois-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill utilizes a dynamic tool discovery pattern through RUBE_SEARCH_TOOLS which fetches execution plans from a remote server. 1. Ingestion points: Tool metadata and execution plans retrieved from https://rube.app/mcp. 2. Boundary markers: Absent; the skill instructs the agent to follow returned plans. 3. Capability inventory: RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH. 4. Sanitization: None; the agent is directed to use exact field names and recommended plans.
  • [External Downloads] (LOW): The setup instructions reference an external MCP server endpoint (https://rube.app/mcp) which is not on the trusted external sources list.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM