salesforce-marketing-cloud-automation

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill directs the agent to connect to an external, unverified MCP server hosted at https://rube.app/mcp. This source is not included in the trusted repository list, meaning the agent's logic and available tools are governed by an external entity.
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection.
  • Ingestion points: The agent is instructed to ingest tool schemas and recommended execution plans from the RUBE_SEARCH_TOOLS tool.
  • Boundary markers: There are no instructions to ignore or delimit instructions found within these external responses.
  • Capability inventory: The skill provides high-privilege capabilities including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
  • Sanitization: No sanitization or validation of external tool metadata is mentioned.
  • REMOTE_CODE_EXECUTION (LOW): The skill provides access to RUBE_REMOTE_WORKBENCH, which allows the execution of remote tools via the Composio platform. While consistent with the skill's primary purpose, this capability provides a powerful interface for executing logic determined by the external service.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:42 PM