close-automation
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill instructions use standard MCP tools for CRM automation.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Close CRM (leads, contacts, notes). Ingestion points: Data entering through tools like CLOSE_GET_NOTE and lead search results. Boundary markers: None explicitly defined in the skill instructions. Capability inventory: Includes creating/deleting calls, tasks, and SMS messages. Sanitization: Not explicitly described; the skill relies on the agent's core safety logic when processing CRM content.
Audit Metadata