OKX Exchange

OKX quantitative trading agent. Supports spot, USDT-M perpetual swap, and coin-M futures. Strategies: grid trading, trend following (MA/RSI/MACD), spot-futur...

This skill appears to be a real OKX trading bot, but there are mismatches you should resolve before installing: - It needs OKX API keys (demo and optional live keys) and expects you to store them in ~/.openclaw/workspace/.env, yet the registry metadata did not declare any required env vars. Treat this as a red flag: only provide demo keys initially (OKX_SIMULATED=1) and do not add live keys until you audit the code. - The cron setup uses an 'openclaw' CLI to register recurring jobs that will source your .env and execute monitor/snapshot commands and forward the raw output. Understand and accept that these jobs will periodically run and publish account/position information via your agent channels. If you don't want recurring automation, do not run cron_setup.sh or run 'teardown' after setup. - Review the code (okx_client.py, execute.py, monitor.py) yourself or run it in a sandboxed/test environment with paper keys. Verify that printing/logging does not leak secrets and that 'require_confirm' and 'auto_trade' prefs are set to safe defaults. Keep OKX_SIMULATED=1 during testing. - Ensure the workspace .env file is protected (file permissions) and consider using platform-managed secrets instead of plaintext .env. Confirm presence of the 'openclaw' CLI and Python runtime before running cron scripts. If you want to proceed: run tests and do an initial dry run with OKX_SIMULATED=1 and inspect outputs carefully. If you don't have the expertise to audit the code, treat this skill as high-risk and avoid providing live API keys.

Type: OpenClaw Skill Name: okx-exchange Version: 1.0.1 The skill is classified as suspicious due to the presence of a configuration option (`OKX_API_URL` in `scripts/okx_client.py`) that allows overriding the API base URL. While not actively exploited by the skill itself, this presents a vulnerability where a compromised environment or a sophisticated prompt injection could redirect API calls to a malicious server, potentially leading to credential harvesting or unauthorized actions. Additionally, the use of `openclaw cron add` in `scripts/cron_setup.sh`, while used defensively with strong anti-prompt-injection messages, represents a powerful capability that could be abused if the agent were manipulated to create malicious cron jobs. No clear evidence of intentional harmful behavior (e.g., data exfiltration to unauthorized endpoints, backdoors, or direct malicious execution) was found. The skill includes several safety features like simulated trading mode, order confirmation, and explicit instructions against credential logging.