← 返回 Skills 市场
124
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install memory-guardian
功能描述
Memory health monitoring, integrity checks, and 3-layer memory architecture for AI agents. Use when agents need to prevent memory loss, detect context overfl...
安全使用建议
This skill bundles a benign-looking file-scanner but its markdown instructions instruct the agent to extract and permanently store credentials and to perform promotions/deletions—behavior not implemented in the shipped script. If you want to use it: (1) Do not run it against a workspace that contains real secrets until you audit and sandbox it. (2) Confirm with the author whether automatic promotion/deletion or credential extraction is implemented; prefer a read-only mode. (3) If you must run it, set OPENCLAW_WORKSPACE to a safe test directory and back up your memory directory first. (4) Ask the publisher to explicitly declare required env vars and to remove any instructions that aggregate credentials into permanent storage or to implement strict safeguards for secrets handling.
功能分析
Type: OpenClaw Skill
Name: memory-guardian
Version: 1.1.0
The skill bundle implements a memory management system for AI agents but contains high-risk instructions in SKILL.md. Specifically, the 'Promotion Protocol' directs the agent to extract and store 'Credentials/keys' into permanent plaintext markdown files (e.g., permanent/user-system.md) to prevent data loss. While the provided script scripts/memory_check.py is a benign diagnostic tool for monitoring file sizes and duplicates, the instruction to store secrets in the workspace is a significant security vulnerability that could lead to credential exposure.
能力评估
Purpose & Capability
The script implements file-scanning, size/staleness/duplicate detection, and index checks under a workspace path—this aligns with a 'memory health' tool. However, the SKILL.md claims broader behaviors (automatic promotions, migrations to FAISS/Neo4j, and an explicit protocol to 'extract: Credentials/keys → permanent') that are not implemented in the code. Asking the agent to extract and centralize credentials is not necessary for a read-only checker and is disproportionate to the stated purpose.
Instruction Scope
Runtime instructions instruct running the provided scanner (fine) but also instruct policy-level actions such as promoting secrets/credentials into permanent storage and deleting session files. Those instructions broaden scope to sensitive data handling. The scanner itself only reads files and prints a report; the SKILL.md gives the agent authority to perform destructive/promotional actions that would affect secrets and long-term storage, which is scope creep and risky.
Install Mechanism
No install spec is provided (instruction-only with a bundled script). No downloads or installers—low installation risk.
Credentials
The code reads OPENCLAW_WORKSPACE (defaulting to ~/.openclaw/workspace) but the skill declares no required environment variables. There's a mismatch between declared requirements and actual behavior. More importantly, the SKILL.md explicitly instructs extracting/storing credentials into permanent memory yet requests no credentials itself—this is an unexplained handling of sensitive data.
Persistence & Privilege
The skill is not set to always:true and does not autonomously modify other skills. The provided script, as written, is read-only: it scans and prints a report. However, the human instructions reference deleting session files and promoting contents, which would be destructive if implemented. At present the code does not implement --fix/auto-repair behavior despite the documentation, which is an implementation mismatch to watch for.
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 memory-guardian - 安装完成后，直接呼叫该 Skill 的名称或使用
/memory-guardian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
v1.1.0
Tightened health check thresholds, clearer 3-layer architecture docs, added migration triggers.
v1.0.0
Initial release of Memory Guardian: streamline memory management and health for AI agents.
- Introduces a 3-layer memory architecture (Working, Permanent, Archive) to prevent memory loss and context overflow.
- Automated health checks catch oversized files, total memory bloat, duplicates, staleness, index inconsistencies, and orphans.
- Defines clear danger zones based on memory usage, with actionable thresholds.
- Outlines strict protocols for promoting critical information before deletion.
- Includes migration triggers for semantic storage backends (e.g., FAISS) as memory grows.
- Provides emergency recovery steps leveraging git history.
元数据
常见问题
Memory Guardian 是什么？
Memory health monitoring, integrity checks, and 3-layer memory architecture for AI agents. Use when agents need to prevent memory loss, detect context overfl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 124 次。
如何安装 Memory Guardian？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install memory-guardian」即可一键安装，无需额外配置。
Memory Guardian 是免费的吗？
是的，Memory Guardian 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Memory Guardian 支持哪些平台？
Memory Guardian 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 Memory Guardian？
由 KairoKid（@dodge1218）开发并维护，当前版本 v1.1.0。
推荐 Skills