cfo-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python scripts (
burn_rate_calculator.py,unit_economics_analyzer.py,fundraising_model.py) designed to be executed by the agent to perform financial modeling. Analysis of these scripts shows they only use the Python standard library, perform mathematical calculations, and output results to the console or CSV format. - [DATA_EXFILTRATION]: No network operations or credential exposure patterns were found. The scripts do not access sensitive file paths or external APIs.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection through the ingestion of company context and user-provided financial metrics.
- Ingestion points: Reads
company-context.mdand processes user-provided values for MRR, burn rate, and hiring plans. - Boundary markers: The skill references the
agent-protocol/SKILL.mdfor quality loops and uses explicit "Key Questions" to structure data collection. - Capability inventory: Execution of local Python scripts for data processing and mathematical modeling.
- Sanitization: Data is parsed into standard numerical types for calculation in the provided Python scripts.
Audit Metadata