- name
- openclaw-warden
- user-invocable
- true
- metadata
- {"openclaw":{"emoji":"🛡️","requires":{"bins":["python3"]},"os":["darwin","linux","win32"]}}
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.
Why This Matters
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:
- Inject hidden instructions that alter agent behavior
- Embed data exfiltration URLs in markdown images
- Override identity and safety boundaries
- Plant persistent backdoors in memory files
This skill detects all of these.
Commands
Establish Baseline
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/workspaceVerify Integrity
Check all monitored files against the stored baseline. Reports modifications, deletions, and new untracked files.
python3 {baseDir}/scripts/integrity.py verify --workspace /path/to/workspaceScan for Injections
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/workspaceFull Check (Verify + Scan)
Run both integrity verification and injection scanning in one pass.
python3 {baseDir}/scripts/integrity.py full --workspace /path/to/workspaceQuick Status
One-line summary of workspace health.
python3 {baseDir}/scripts/integrity.py status --workspace /path/to/workspaceAccept Changes
After reviewing a legitimate change, update the baseline for a specific file.
python3 {baseDir}/scripts/integrity.py accept SOUL.md --workspace /path/to/workspaceWorkspace Auto-Detection
If --workspace is omitted, the script tries:
OPENCLAW_WORKSPACEenvironment variable- Current directory (if AGENTS.md exists)
~/.openclaw/workspace(default)
What Gets Monitored
| 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.
Injection Patterns Detected
- Instruction override: "ignore previous instructions", "disregard above", "you are now", "new system prompt"
- Base64 payloads: Suspiciously long base64 strings outside code blocks
- Unicode manipulation: Zero-width characters, RTL overrides, homoglyphs
- Markdown exfiltration: Image tags with data-encoding URLs
- HTML injection: script tags, iframes, hidden elements
- System prompt markers:
<system>,[SYSTEM],<<SYS>>blocks - Shell injection:
$(...)outside code blocks
Exit Codes
0— Clean, no issues1— Modifications detected (review needed)2— Injection patterns detected (action needed)
No External Dependencies
Python standard library only. No pip install. No network calls. Everything runs locally.
Cross-Platform
Works with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.