Trading DevBox

Trading strategy development sandbox. User describes trading intent in natural language, agent writes a Python backtest strategy and returns results.

This skill is internally inconsistent: it says it will run backtests and return results but the runtime instructions only write a template script to /tmp and print a placeholder; it doesn't provide data sources or dependency installation steps (backtrader is imported but not installed). Before installing or running this skill: 1) Ask the author to clarify how market data is obtained and where results are stored; 2) Request explicit, pinned install steps for dependencies (e.g., pip install backtrader==<version>) rather than leaving the agent to fetch packages; 3) Require the agent to seek explicit user confirmation before executing any generated code or installing packages; 4) Run the skill in an isolated/containerized environment and review the generated strategy.py before execution to avoid arbitrary code running on your machine; 5) If the skill will access exchange APIs, ensure it requests only the minimal credentials needed and documents how they are used. These changes would resolve the main incoherences; absent them, treat the skill cautiously.

Type: OpenClaw Skill Name: trading-devbox Version: 0.1.0 The skill bundle describes a 'trading-devbox' for generating and backtesting trading strategies. The `SKILL.md` contains instructions for the AI agent to parse user intent, confirm parameters, and generate a Python backtest strategy. The embedded shell commands (`mkdir`, `cat`, `python3`) are used to write and execute a fixed, self-contained Python script (`strategy.py`) in a temporary directory. This Python script uses the `backtrader` library for a basic trading simulation and does not contain any malicious code, network calls, file system access beyond its own execution, or attempts to exfiltrate data. There are no prompt injection attempts within the `SKILL.md` instructions that would lead the agent to deviate from its stated purpose or perform harmful actions. The skill's core functionality involves code generation, which inherently carries risk if the agent's generation logic is flawed, but the provided skill bundle itself does not demonstrate or instruct malicious exploitation of this capability.