salesforce-marketing-cloud-automation

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill uses RUBE_SEARCH_TOOLS to retrieve tool slugs and schemas at runtime, which are then executed via RUBE_MULTI_EXECUTE_TOOL. This dynamic resolution model depends on the integrity of the remote server's responses to define agent behavior.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources including Salesforce Marketing Cloud and remote tool schemas.\n
  • Ingestion points: Data returned from search queries, recommended execution plans, and Salesforce tool outputs (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters or specific instructions to the agent to ignore instructions embedded in the processed data.\n
  • Capability inventory: Capabilities include tool execution via RUBE_MULTI_EXECUTE_TOOL and remote functionality via RUBE_REMOTE_WORKBENCH (SKILL.md).\n
  • Sanitization: The instructions do not describe any sanitization, validation, or filtering mechanisms for the data retrieved from external tools or services.\n- [EXTERNAL_DOWNLOADS]: The skill requires connecting to a remote MCP endpoint at https://rube.app/mcp for core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:28 AM
Security Audit — agent-trust-hub — salesforce-marketing-cloud-automation