live-dashboard
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill coordinates several Model Context Protocol (MCP) tools, including Google Analytics, Google Ads, Meta Ads, and CRM integrations, to aggregate marketing metrics. These interactions are standard for the skill's purpose and are performed within a controlled tool-calling environment.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to the ingestion of data from external marketing APIs. Ingestion points: Local brand context files and metadata from connected marketing accounts (e.g., campaign names). Boundary markers: None identified in the prompt logic. Capability inventory: Data retrieval and configuration execution through marketing MCPs. Sanitization: The skill relies on the structured nature of the data provided by connected third-party marketing platforms.
Audit Metadata