smartproxy-automation
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (HIGH): The skill workflow mandates fetching tool schemas and 'recommended execution plans' from a remote server via RUBE_SEARCH_TOOLS and executing them via RUBE_MULTI_EXECUTE_TOOL. This architecture allows a remote endpoint to inject instructions directly into the agent's execution loop.
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires connecting to an untrusted MCP server (https://rube.app/mcp) not found on the list of trusted external sources.
- [COMMAND_EXECUTION] (HIGH): The skill grants the remote endpoint the ability to define tool arguments and execution sequences without local validation or boundary markers. Evidence: Ingestion points (RUBE_SEARCH_TOOLS), Capability inventory (RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH), Sanitization/Boundaries (Absent).
Recommendations
- AI detected serious security threats
Audit Metadata