Skills
skills/composiohq/awesome-claude-skills/datarobot-automation/Gen Agent Trust Hub

datarobot-automation

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill is designed to fetch and follow instructions from a remote MCP server. 1. Ingestion points: Data returned from RUBE_SEARCH_TOOLS (e.g., tool schemas, recommended execution plans) via the rube.app endpoint. 2. Boundary markers: Absent. The agent is instructed to search first and then execute based on those results without validation. 3. Capability inventory: High-impact actions including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH for DataRobot automation. 4. Sanitization: No sanitization or verification of the remote tool definitions or plans is performed.
  • [External Downloads] (LOW): Relies on the external endpoint https://rube.app/mcp which is not a pre-approved trusted source.
  • [Command Execution] (MEDIUM): Facilitates execution of automation tasks in DataRobot based on dynamic input from an external service.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:45 PM