use-twenty-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Twenty CRM records and metadata, which creates a potential surface for indirect prompt injection if the CRM content contains malicious instructions.
- Ingestion points: Data is retrieved from an external Twenty workspace via the Model Context Protocol (MCP).
- Capability inventory: The skill retrieves, lists, searches, and summarizes CRM records and workspace metadata.
- Boundary markers: The instructions do not specify any boundary markers or delimiters to separate CRM data from agent instructions.
- Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from the CRM before it is processed by the agent.
Audit Metadata