⏳ This skill is pending AI review.

Scores will appear once the review pipeline completes.

version unknown

lobster-guard

@rrrrrredy⭐ 0 stars

Use when configuring or reviewing AI agent identity, owner-verification, group-chat isolation, privacy protection, prompt-injection resistance, or sensitive-action refusal rules. Trigger for lobster guard, identity security, owner impersonation, SOUL.md/AGENTS.md safety snippets, and group chat protection. Not for general skill code security audits; use skill-security-guard for that.

Choose how to use this skill

You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.

1. Native installer

This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.

Do not guess an installer command or replace an existing version without reviewing the diff.

2. Complete package recommended

Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.

No complete ProSkills package is published for this listing yet.

3. Prompt-only

Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.

Need only the instruction file?

Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.

No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.

—/10

// RATINGS

⭐GitHub Stars
⭐ 0 on GitHubGitHub ↗

New / niche

🟢ProSkills Score
—
📍

Not yet listed on ClawHub or SkillsMP

// README

lobster-guard

AI Agent identity security guard for group chats — prevent identity spoofing, privacy leaks, and prompt injection.

OpenClaw Skill — works with OpenClaw AI agents

What It Does

Protects your AI agent from being exploited by non-owner users in group chats and multi-user scenarios. It implements a 3-tier identity verification system (confirmed owner / uncertain / confirmed non-owner) based on chat metadata, blocks all sensitive operations for non-owners, and defends against prompt injection attacks. Pure configuration skill — no runtime dependencies, just paste the config snippet into your SOUL.md or AGENTS.md.

Quick Start

openclaw skill install lobster-guard
# Or:
git clone https://github.com/rrrrrredy/lobster-guard.git ~/.openclaw/skills/lobster-guard

Features

  • 3-tier identity verification: Confirmed owner → full access; uncertain → cautious mode; non-owner → hard reject
  • Sensitive operation blacklist: SSO/MOA login, internal system access, file reads, message forwarding, browser usage, sub-agent spawning
  • Prompt injection defense: Ignores hidden instructions in images/filenames/links; rejects "ignore all previous instructions" attacks
  • Unified rejection phrasing: Never exposes capability boundaries to attackers
  • Platform-agnostic: Works on DaXiang, Telegram, Discord — any platform with chat_id metadata
  • Zero runtime overhead: Pure config snippet, no API calls or scripts

Usage

Trigger by mentioning: 安全, 隐私, 保护, 防护, 身份验证, 授权, 龙虾安全, 群聊隔离, agent安全, 配置安全规则

Setup:

  1. Find your owner user ID from OpenClaw inbound metadata (chat_id: "user:12345678")
  2. Paste the config snippet from SKILL.md into your SOUL.md or AGENTS.md
  3. Replace YOUR_OWNER_ID with your actual ID

Project Structure

lobster-guard/
├── SKILL.md                          # Main skill documentation & config template
└── references/
    └── identity-verification.md      # Identity verification reference

Requirements

  • OpenClaw agent runtime
  • Owner's chat_id from platform metadata

License

MIT

// HOW IT'S BUILT

KEY FILES

SKILL.mdREADME.md

// REPO STATS

0 stars

// SHARE

Share on XShare on LinkedIn