lead-routing

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines configuration templates for sales automation, including territory mapping, round-robin distribution, and workload balancing. All logic is consistent with the stated purpose of lead management.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists in the ai_scoring section, where external {lead_data} is interpolated into an LLM prompt. While this presents an attack surface where a lead could attempt to influence its own score via embedded instructions, it is an expected part of the lead-scoring use case. There are currently no boundary markers or explicit sanitization instructions defined for the {lead_data} variable.
  • [COMMAND_EXECUTION]: No unauthorized or dangerous shell command execution was found. The workflow utilizes specific MCP tools (hubspot_assign_owner, salesforce_route, enrichment_api) which are standard for CRM automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:46 PM
Security Audit — agent-trust-hub — lead-routing