agent-access-control
Tiered stranger access control for AI agents. Use when setting up contact permissions, handling unknown senders, managing approved contacts, or configuring stranger deflection on messaging platforms (WhatsApp, Telegram, Discord, Signal). Provides diplomatic deflection, owner approval flow, and multi-tier access (owner/trusted/chat-only/blocked).
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bowen31337/agent-access-controlWhat This Skill Does
The agent-access-control skill provides a robust security layer for OpenClaw AI agents operating on messaging platforms like WhatsApp, Telegram, Discord, and Signal. It acts as a digital gatekeeper, ensuring that your agent's capabilities—ranging from basic chitchat to sensitive data access—are strictly gated behind a multi-tier permission system. The skill features an automated 'stranger deflection' mechanism that politely informs unsolicited contacts that the agent is currently unavailable, while simultaneously pinging the owner for manual verification. By centralizing contact management through a simple JSON configuration, this skill prevents unauthorized tool usage and protects your privacy.
Installation
To add this layer of security to your agent, run the following command in your terminal:
clawhub install openclaw/skills/skills/bowen31337/agent-access-control
After installation, initialize the security protocol by creating memory/access-control.json within your workspace. Configure the ownerIds array, define your strangerMessage, and set the notifyChannel and notifyTarget parameters to ensure alerts reach your primary messaging app.
Use Cases
- Personal Assistants: Keep your private AI free from spam or unwanted interruptions while maintaining a polite persona.
- Team Management: Regulate access within group chats by upgrading colleagues to 'Trusted' status while keeping unknown external users at bay.
- Privacy-First Operations: Ensure that internal tools and memory files are strictly inaccessible to anyone other than the verified owner.
- Professional Gatekeeping: Act as an automated secretary that triages incoming messages, allowing you to manually approve who gets to interact with your agent.
Example Prompts
- "Check my pending approvals and upgrade John Doe to a Trusted contact so he can use the weather tool."
- "Add +1-555-0199 to the blocked list immediately; they keep spamming the agent."
- "Change the agent's stranger deflection message to be more formal and mention that I am currently on vacation."
Tips & Limitations
- Normalization is Key: Always ensure phone numbers include the international country code prefix to avoid mapping errors during the ID check phase.
- Tier Strategy: Use the 'Chat-only' tier for acquaintances you want to talk to, but avoid giving them access to your file system or automation tools.
- Maintenance: Regularly audit your
approvedContactslist to revoke access for users who no longer require it. - Limitations: The skill currently relies on the messaging platform's API availability; ensure your network connection is stable for real-time owner notifications to function correctly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bowen31337-agent-access-control": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write
Related Skills
Terse
Skill by bowen31337
Identity Resolver
Skill by bowen31337
agent-self-governance
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging). Use when: (1) receiving a user correction — log it before responding, (2) making an important decision or analysis — log it before continuing, (3) pre-compaction memory flush — flush the working buffer to WAL, (4) session start — replay unapplied WAL entries to restore lost context, (5) any time you want to ensure something survives compaction, (6) before claiming a task is done — verify it, (7) periodic self-check — am I drifting from my persona? (8) cost tracking — was that expensive operation worth it? (9) discovering infrastructure — log hardware/service specs immediately.
rsi-loop
Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect their own failure patterns and generate concrete improvement proposals (new skills, routing fixes, SOUL.md updates, memory improvements). Use when: (1) logging a task outcome (success/fail/quality), (2) running periodic self-improvement analysis, (3) reviewing or deploying improvement proposals, (4) integrating RSI into EvoClaw hub/edge agents via MQTT, (5) checking agent health score, (6) any mention of "self-improvement", "recursive improvement", "fix my own mistakes", "improvement loop", or "agent evolution". Core EvoClaw primitive.
clawchain
ClawChain RPC client for EvoClaw agents. Connects to Substrate-based blockchain, queries on-chain agent data, submits transactions, and enables agents to participate in on-chain governance and reputation tracking. Use when working with ClawChain L1 blockchain, agent DIDs, token economics, or agent reputation systems.