Openclaw Sec

AI Agent Security Suite - Real-time protection against prompt injection, command injection, SSRF, path traversal, secrets exposure, and content policy violat...

This package largely implements what it claims (a local security validator), but it contains intrusive install scripts and high-impact runtime behaviors. Before installing or enabling: 1) Inspect the two plugin install scripts (plugins/*/install.ts) — they write to ~/.openclaw/openclaw.json and will enable the plugins automatically; do not run them unless you trust the code. 2) Review plugin code (plugins/*/index.ts) and the security engine usage: note that the plugin can open a local DB, log events, and return a systemPrompt that forces model replies on block. 3) Check and edit the example config (.openclaw-sec.example.yaml) — remove or review owner_ids and notification webhooks, and set logging/database paths you control. 4) If you only want validation without persistent integration, avoid running the install scripts and call the CLI/tool manually in an isolated environment. 5) If you lack time to audit code, run the skill in a disposable sandbox or container first and do not provide production credentials. If you want, I can point out the exact lines that modify ~/.openclaw/openclaw.json and where the systemPrompt is composed.

Type: OpenClaw Skill Name: openclaw-sec-plus Version: 0.1.1 The bundle is a comprehensive and well-engineered security suite for AI agents, providing multi-module detection for prompt injection, command injection, SSRF, path traversal, and secrets exposure. The code architecture is professional, featuring structured logging (logger.ts), local event storage using SQLite (database-manager.ts), and a configurable notification system (notification-system.ts). The included OpenClaw plugins (security-input-validator-plugin and security-tool-validator-plugin) correctly implement defensive hooks to intercept and validate agent inputs and tool calls. All behaviors, including the use of regex patterns for threat detection and the automated installation scripts, are entirely consistent with the stated purpose of a defensive security tool.