close-crm

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for using Model Context Protocol (MCP) tools to interact with Close CRM. It includes best practices for data safety, such as requiring user confirmation for writes and deletions, and respecting OAuth scopes. All referenced URLs belong to the official vendor domain (close.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection, as it processes data from external CRM records (leads, activities, notes). However, the skill provides specific instructions to mitigate this risk, such as requiring summaries of changes before execution and explicit confirmation for irreversible actions like deletions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 04:44 PM