customer-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of customer data from e-commerce platforms (Shopify, WooCommerce, BigCommerce) and custom databases.
- Ingestion points: Evaluation tasks in the evals/ directory (e.g., evals/rfm-scoring-pipeline-and-segment-classif/task.md) describe processing data from the orders and customers tables, which are populated by external customer activity.
- Boundary markers: Absent; the instructions and evaluation tasks do not suggest the use of delimiters or "ignore instructions" warnings to isolate untrusted data from the processing logic.
- Capability inventory: The skill enables SQL execution for RFM scoring and TypeScript functions for churn prediction.
- Sanitization: The instructions do not mandate sanitization or validation of customer-supplied text fields, which could contain malicious prompts if processed by an LLM.
Audit Metadata