Security hardening for AI agents - Moltbot, OpenClaw, Cursor, Claude. Lock down gateway, fix permissions, auth, firewalls. Essential for vibe-coding setups.
Scan AI agent skills for malware, credential theft, prompt injection, and dangerous permissions before installing them
Add 8 security governance layers to your OpenClaw agent — budget controls, permissions, audit logging, kill switch, identity signing, skill vetting, process isolation, and gateway protection.
Use when you need to control Discord from Clawdbot via the discord tool: send messages, react, post or upload stickers, upload emojis, run polls, manage threads/pins/search, fetch permissions or membe
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or ana
Build the Clawdbot macOS menu bar app from source. Use when you need to install the Clawdbot.app companion (for menu bar status, permissions, and Mac hardware access like camera/screen recording). Han
Audit AWS IAM policies and roles for over-privilege, wildcard permissions, and least-privilege violations
Checks whether credentials and tokens are stored safely. Validates file permissions, plaintext exposure, git repo contamination, log redaction coverage, and...
Generate a complete App Store deliverable pack for a Flutter 3.35.1 app with offline-first design, camera/photo permissions, Apple-style UI mockups, and a sq...
Security hardening for AI agents. Audit your workspace for leaked secrets, check file permissions, validate API key storage, scan for prompt injection risks,...
Analyze smart contracts, token mechanics, permissions, fee flows, upgradeability, market risks, and likely attack surfaces for onchain projects. Use when rev...
--- name: jules-tools-skill version: 1.0.0 description: "Interface with Google's Jules Tools CLI to manage AI coding sessions." permissions: exec: - jules - npm --- # Jules Tools Skill Thi
Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, su
--- name: multi-user-workspace description: Multi-user workspace management with sandbox permissions, user profiles, and relationship networks. --- # Friends Configure per-user sessions with sandbox
Supervise a main agent so it defaults to execution, suppresses obvious permission loops, and escalates to the user only for true approvals or critical ambigu...
Provide secure, permission-controlled access to Firebase Firestore databases through a standardized MCP interface. Enable AI assistants and other clients to perform full CRUD operations, advanced quer
Key lifecycle management with Volcengine KMS. Use when users need key creation, rotation policies, encryption/decryption workflows, or key permission troubleshooting.
Runs a backend-backed live safety check for instructions that may trigger tool execution, external calls, file edits, permission changes, destructive or irre...
A robust, permission-friendly method to capture macOS screens via OpenClaw screen.record. Ideal for headless environments or ensuring capture reliability.