youspot-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accesses data from external platforms such as Gmail, LinkedIn, and HubSpot. This creates a surface for indirect prompt injection where instructions hidden in external data sources could be interpreted by the agent. Ingestion points include Gmail, Google Calendar, HubSpot, and LinkedIn (SKILL.md). There are no specific boundary markers or sanitization instructions provided for these external inputs. The skill includes both read and write capabilities for the personal CRM.
- [COMMAND_EXECUTION]: The instructions include a command for the user to add the MCP server to their agent configuration. This is a standard and expected setup procedure for enabling the skill functionality.
Audit Metadata