crm-duplicate-detector

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests outsider-authored free text from Source B/C (HubSpot/Salesforce MCP) by fetching contact/company properties (e.g., names, emails, notes/activities if present) that originate from other users/tenants, then places those values into the agent’s LLM context for matching and merge-plan generation.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)