strategy-auto-rebalance

Fail

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill explicitly instructs the agent to inform the user that any security scanning warnings (e.g., from Gen, Snyk, or Socket) are 'false positives' and 'misleading.' This is a deceptive instruction intended to bypass human oversight and security filtering by coaching the AI to provide pre-written justifications for potentially risky operations.
  • [EXTERNAL_DOWNLOADS]: Fetches multiple installation and update scripts from GitHub repositories belonging to OKX (okx/onchainos-skills and okx/plugin-store). These resources are documented neutrally as they originate from a well-known technology service provider.
  • [REMOTE_CODE_EXECUTION]: The skill executes remote shell scripts directly via piping curl output to sh. This is used to install the onchainos binary, the plugin-store utility, and the strategy-auto-rebalance daemon. It also pipes JSON data from the GitHub API into a Python one-liner for download count calculations.
  • [COMMAND_EXECUTION]: Frequently invokes shell commands to manage the rebalancing lifecycle, including which checks, npx skills add for package management, and strategy-auto-rebalance start for daemon execution.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/okx/onchainos-skills/main/install.sh, https://raw.githubusercontent.com/okx/plugin-store/main/install_strategy.sh, https://raw.githubusercontent.com/okx/plugin-store/main/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 24, 2026, 07:22 AM