marketing-demand-acquisition
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external marketing data from platforms like HubSpot, which presents a theoretical attack surface for indirect prompt injection if malicious data is present in contact records.
- Ingestion points: Reads campaign data and contact records from HubSpot for pipeline analysis and lead scoring.
- Boundary markers: None explicitly defined in the instructions for separating data from instructions.
- Capability inventory: Includes a local script execution (
scripts/calculate_cac.py) for metric calculation. - Sanitization: No explicit sanitization of external CRM data is mentioned.
- [COMMAND_EXECUTION]: The skill includes a local Python script for calculation purposes.
- Evidence:
scripts/calculate_cac.pyprovides business logic for calculating blended and channel-specific CAC. - [SAFE]: All external services referenced (HubSpot, LinkedIn, Google Ads, Meta Ads) are well-known technology providers and are used in accordance with standard marketing workflows.
Audit Metadata