demand-forecasting
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which is a potential vector for indirect instructions.
- Ingestion points: The skill ingests sales lines, stock balances, and product/branch master data from external systems like POS or ERP exports as defined in the 'Required Inputs' section of
SKILL.md. - Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to wrap external data (e.g., using XML tags) to prevent the agent from confusing data with instructions.
- Capability inventory: The agent has the capability to execute SQL queries (defined in
references/demand_forecasting.md) against database exports or replicas to analyze the data. - Sanitization: The skill does not explicitly mention sanitizing the content of the data files or filtering for potentially malicious strings within product names or status fields.
Audit Metadata