research-business
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust framework for business intelligence and research. Key safety features include:
- Explicit prohibitions against unauthorized actions such as purchasing reports, contacting individuals, or disclosing private data without user confirmation.
- Strong emphasis on citation integrity with instructions to never fabricate sources.
- Guidance on distinguishing between verified facts and estimated assumptions.
- [DATA_EXPOSURE]: The skill operates on local context files located in the
.business/directory. It includes specific warnings to protect private company data and requires authorization before external disclosure, mitigating exfiltration risks. - [PROMPT_INJECTION]: The skill instructions do not contain any patterns designed to bypass agent safety filters or override system instructions. It focuses strictly on the research task methodology.
Audit Metadata