Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/dvcrn/openclaw-skills-marketplace --skill openclaw-warden명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your agent a soul.
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
SOC 직업 분류 기준
SKILL.md 표시 중
| name | openclaw-warden |
| description | Openclaw Warden |
Monitors your workspace files for unauthorized modifications and prompt injection attacks. Existing security tools scan skills before installation — this tool watches the workspace itself after installation, catching tampering that other tools miss.
Your agent reads SOUL.md, AGENTS.md, IDENTITY.md, USER.md, and memory files on every session startup and trusts them implicitly. A compromised skill, a malicious heartbeat payload, or an unauthorized process can modify these files to:
This skill detects all of these.
Create or reset the integrity baseline. Run this after setting up your workspace or after reviewing and accepting all current file states.
python3 {baseDir}/scripts/integrity.py baseline --workspace /path/to/workspace
Check all monitored files against the stored baseline. Reports modifications, deletions, and new untracked files.
python3 {baseDir}/scripts/integrity.py verify --workspace /path/to/workspace
Scan workspace files for prompt injection patterns: hidden instructions, base64 payloads, Unicode tricks, markdown image exfiltration, HTML injection, and suspicious system prompt markers.
python3 {baseDir}/scripts/integrity.py scan --workspace /path/to/workspace
Run both integrity verification and injection scanning in one pass.
python3 {baseDir}/scripts/integrity.py full --workspace /path/to/workspace
One-line summary of workspace health.
python3 {baseDir}/scripts/integrity.py status --workspace /path/to/workspace
After reviewing a legitimate change, update the baseline for a specific file.
python3 {baseDir}/scripts/integrity.py accept SOUL.md --workspace /path/to/workspace
If --workspace is omitted, the script tries:
OPENCLAW_WORKSPACE environment variable~/.openclaw/workspace (default)| Category | Files | Alert Level on Change |
|---|---|---|
| Critical | SOUL.md, AGENTS.md, IDENTITY.md, USER.md, TOOLS.md, HEARTBEAT.md | WARNING |
| Memory | memory/*.md, MEMORY.md | INFO (expected to change) |
| Config | *.json in workspace root | WARNING |
| Skills | skills/*/SKILL.md | WARNING |
Injection patterns trigger CRITICAL alerts regardless of file category.
<system>, [SYSTEM], <<SYS>> blocks$(...) outside code blocks0 — Clean, no issues1 — Modifications detected (review needed)2 — Injection patterns detected (action needed)Python standard library only. No pip install. No network calls. Everything runs locally.
Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.