first-party-data-collection

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of markdown instructions and evaluation criteria for training or testing AI agents on marketing data strategies. No executable code is bundled with the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation references well-known and trusted services including Shopify, WooCommerce, Klaviyo, Typeform, and Octane AI. These are standard industry integrations for the stated purpose of the skill.
  • [DATA_EXFILTRATION]: While the skill discusses collecting customer data (e.g., email, preferences), it does so within the context of legitimate marketing operations and emphasizes privacy compliance (GDPR/CCPA). It does not contain any logic for unauthorized data exfiltration.
  • [PROMPT_INJECTION]: The evaluation tasks (task.md) use standard instructional framing to define scenarios for an AI agent. No attempts to bypass safety filters or override system instructions were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 12:44 PM