genpark-automated-email-marketing-agent-skill

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include cloning a repository from an external source at github.com/alphaparkinc/genpark-automated-email-marketing-agent-skill.git and installing dependencies via pip.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to generate and deploy marketing campaigns, creating a surface for indirect prompt injection.
  • Ingestion points: example_emails file paths, brand_voice strings, product_description inputs, and user_data dictionaries used in the sequence generation and personalization engines.
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: The agent has the capability to generate AI content and programmatically send emails through SendGrid and Mailgun integrations.
  • Sanitization: No explicit sanitization, filtering, or validation of the input strings is shown before they are passed to the AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 09:53 PM