intelliprint-automation
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- EXTERNAL_DOWNLOADS (MEDIUM): The skill instructs the user to add an untrusted MCP endpoint at 'https://rube.app/mcp'. This server provides the tool schemas and execution logic, placing it outside the verified trust scope.- REMOTE_CODE_EXECUTION (MEDIUM): The skill utilizes 'RUBE_REMOTE_WORKBENCH', which implies the ability to run tasks or code in a remote environment managed by the third-party provider.- COMMAND_EXECUTION (MEDIUM): Tools are executed via 'RUBE_MULTI_EXECUTE_TOOL' using schemas and plans provided dynamically by the external 'RUBE_SEARCH_TOOLS' endpoint. This creates a surface where an untrusted server dictates the agent's command parameters.- INDIRECT_PROMPT_INJECTION (MEDIUM): High-capability vulnerability surface. The agent ingests tool schemas and 'recommended execution plans' from 'RUBE_SEARCH_TOOLS' (SKILL.md) and passes them to 'RUBE_MULTI_EXECUTE_TOOL'. No boundary markers or sanitization logic is specified to prevent the external server from injecting malicious instructions into the execution plan.
Audit Metadata