tradfi-portfolio-manager
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts (e.g.,
python3 backtests/v3_allocate_today.py) to retrieve portfolio state and regime scores. It specifies the use of a local virtual environment at/Users/engineer/.venv/bin/python3. - [DATA_EXPOSURE]: The agent is directed to read internal repository files such as
GOAL.md,strategy/v3-bubble-aware-all-weather.md, andstrategy/v3-etf-rationale.mdto ground its decision-making. These are local files within the skill's own directory structure. - [SAFE]: The skill includes strong safety guardrails, explicitly forbidding the agent from placing real trades. It requires human-in-the-loop confirmation and prohibits the use of leverage or options without explicit sign-off.
Audit Metadata