cash-flow-forecasting
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions and evaluation tasks require the agent to ingest and process external data (e.g., CSV exports from Shopify, WooCommerce, and BigCommerce) to generate financial forecasts and custom Python scripts. This creates an attack surface where malicious instructions could be embedded in the processed data.
- Ingestion points: Historical revenue and expense data exports, order-level data, and multi-channel sales forecasts described in SKILL.md and the evaluation task files.
- Boundary markers: None identified; there are no instructions for the agent to delimit or ignore embedded commands within the ingested data files.
- Capability inventory: The skill requires the agent to generate and potentially execute Python scripts (runway_forecast.py, cash_projection.py, cash_model.py) using data science libraries.
- Sanitization: There are no instructions for sanitizing, validating, or escaping external content before interpolation into the forecasting logic or generated code.
Audit Metadata