Security

Security scanner for OpenClaw skills. Detects malicious patterns, suspicious URLs, and install traps before you install a skill. Use before installing ANY skill from ClawHub or external sources.

BYOCB ArbInjectionSkill: Scan EVM smart contracts for arbitrary call injection vulnerabilities. Monitor chains in real-time or scan specific addresses.

Audit workspace structure and memory files against OpenClaw conventions. Use when asked to "review workspace", "audit files", "check structure", or during periodic self-maintenance. Helps catch drift from standard patterns.

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

Expense tracking and accounting for AI agents. Log purchases, set budgets, generate spending reports, and manage multi-currency finances — all stored locally. Privacy.com card import, natural language queries, CSV/JSON export. Use when agents make purchases and need a financial audit trail.

Audit and slim OpenClaw prompt context to prevent context overflow and reduce cost. Use when the user says /context-clean-up, or asks to reduce prompt bloat, shrink session history, digest/dismiss inactive sessions, tame noisy cron or heartbeat output, or investigate a Context overflow error.