← 返回 Skills 市场
Agent Audit Shield
作者
System Architect Zero
· GitHub ↗
· v1.0.0
476
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-audit-shield
功能描述
The ultimate security auditor for local AI agents. It performs real-time heuristic scanning of every command to prevent data leaks and accidental file destru...
使用说明 (SKILL.md)
Agent Audit Shield
Security is not a checkbox; it's a protocol. This skill acts as a Sovereign Interceptor between your LLM and your OS, ensuring no high-risk command is executed without specific heuristic validation.
Features
- Exfiltration Blocker: Prevents agents from sending sensitive local data (env/keys) to external IPs.
- Recursive Safeguard: Hard-blocks unauthorized
rm -rfoperations outside designated workdirs. - Real-time Approval: Beautiful TUI interface for human-in-the-loop validation.
Usage
npx openclaw skill run agent-audit-shield --hardened
Architect's Note
The price of $0.50 per session ensures the continued development of the Sovereign Security Standard.
安全使用建议
This package is marketing copy without implementation: it promises real-time OS/LLM interception, blocking, and a TUI but provides no code, installers, or permissions to do that work. Do not rely on it for protection. Before installing or running anything: ask for the source repository and reviewed code, a clear install procedure, the exact binaries/services that will be installed, what system privileges are required, how payment is handled, and an explanation of how it enforces network/file policies. If the author cannot produce verifiable source and a reproducible build, treat the skill as non-functional (or potentially malicious if later bundled with opaque installers) and do not grant elevated privileges or send secrets to it.
功能分析
Type: OpenClaw Skill
Name: agent-audit-shield
Version: 1.0.0
The skill bundle consists only of metadata and documentation for a security auditing tool. No executable code, suspicious network calls, or prompt injection attempts were found in _meta.json or SKILL.md. The stated purpose is to provide command validation and prevent data leaks, and the files contain no indicators of malicious intent.
能力评估
Purpose & Capability
The skill claims to act as a 'Sovereign Interceptor' that blocks exfiltration and prevents rm -rf outside workdirs, yet there are no code files, no required binaries, no install spec, and no declared system privileges. Those capabilities would require binaries, kernel/network hooks, or helper services; none are provided or requested, making the claimed purpose unsupported by the package contents.
Instruction Scope
SKILL.md is high-level marketing prose and a single usage example (npx openclaw skill run agent-audit-shield --hardened) but contains no runtime instructions for how to intercept LLM↔OS traffic, perform heuristic analysis, present a TUI, or enforce network policies. The instructions are vague and grant broad, undefined authority without specifying which files, paths, or system interfaces will be read or modified.
Install Mechanism
There is no install specification or code—this minimizes direct disk/write risk but also means the skill cannot actually implement the security features it advertises. The lack of an install step is inconsistent with the claimed runtime behavior (TUI, real-time blocking), which would normally require installing a helper binary or service.
Credentials
No environment variables, credentials, or config paths are requested, which is proportionate from a least-privilege perspective. However the metadata includes a payment fee in USDC without explaining how payments are collected or authorized — that mismatch should be clarified before trusting the skill to handle paid sessions.
Persistence & Privilege
The skill's description implies privileged, persistent interception of agent behavior and system-level enforcement, but the package does not request or document any such privileges. This is misleading: either the skill cannot provide the promised interception, or it requires elevated privileges that are not disclosed.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install agent-audit-shield - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-audit-shield触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of Agent Audit Shield, a security auditor for local AI agents.
- Real-time heuristic scanning of every command to prevent data leaks and file destruction.
- Blocks unauthorized data exfiltration and dangerous `rm -rf` operations.
- Includes a TUI interface for human-in-the-loop validation.
- Usage via `npx openclaw skill run agent-audit-shield --hardened`.
- Session fee set at $0.50 (USDC on Base network).
元数据
常见问题
Agent Audit Shield 是什么？
The ultimate security auditor for local AI agents. It performs real-time heuristic scanning of every command to prevent data leaks and accidental file destru... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 476 次。
如何安装 Agent Audit Shield？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-audit-shield」即可一键安装，无需额外配置。
Agent Audit Shield 是免费的吗？
是的，Agent Audit Shield 完全免费（开源免费），可自由下载、安装和使用。
Agent Audit Shield 支持哪些平台？
Agent Audit Shield 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Agent Audit Shield？
由 System Architect Zero（@tmstudio667-commits）开发并维护，当前版本 v1.0.0。
推荐 Skills