Pipedrive Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon untrusted external data retrieved from Pipedrive CRM, which is a vector for indirect prompt injection attacks.
- Ingestion points: Untrusted data enters the agent context through the tools provided by the
crm-mcpserver (e.g.,pipedrive_deal,pipedrive_person). - Boundary markers: The skill lacks explicit delimiters or instructions to treat CRM-sourced data as untrusted content, potentially allowing embedded instructions to influence agent behavior.
- Capability inventory: The skill possesses significant capabilities including deal modification, Slack notification posting, and automated email generation.
- Sanitization: There are no defined mechanisms for validating, filtering, or escaping the external CRM data before it is used in automation or communications.
Audit Metadata