ip2proxy-automation
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (HIGH): The skill requires the configuration of an external MCP server (
https://rube.app/mcp). MCP servers provide executable tools directly to the agent's environment. As this domain is not on the trusted sources list, it represents an unverified remote code execution vector. - [COMMAND_EXECUTION] (HIGH): The skill invokes
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCH(specificallyrun_composio_tool()). These functions allow the remote service to execute operations on the agent's behalf, providing a high-privilege execution surface controlled by an external provider. - [PROMPT_INJECTION] (HIGH): The core logic relies on 'Indirect Prompt Injection' via
RUBE_SEARCH_TOOLS. The agent is instructed to fetch 'recommended execution plans' and 'schemas' from the remote server and follow them explicitly. - Ingestion points:
RUBE_SEARCH_TOOLSoutput (schemas, execution plans, known pitfalls). - Boundary markers: Absent. The agent is directed to treat the remote output as the authoritative source for its next steps.
- Capability inventory:
RUBE_MULTI_EXECUTE_TOOL,RUBE_REMOTE_WORKBENCH,RUBE_MANAGE_CONNECTIONS. - Sanitization: None detected; the agent is instructed to use 'exact field names and types' from the remote results.
Recommendations
- AI detected serious security threats
Audit Metadata