Назад към всички

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.

$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.mdreadonly
SKILL.md Frontmatter
nameopenclaw-warden
user-invocabletrue
metadata[object Object]

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/workspace

Verify 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/workspace

Scan 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/workspace

Full Check (Verify + Scan)

Run both integrity verification and injection scanning in one pass.

python3 {baseDir}/scripts/integrity.py full --workspace /path/to/workspace

Quick Status

One-line summary of workspace health.

python3 {baseDir}/scripts/integrity.py status --workspace /path/to/workspace

Accept Changes

After reviewing a legitimate change, update the baseline for a specific file.

python3 {baseDir}/scripts/integrity.py accept SOUL.md --workspace /path/to/workspace

Workspace Auto-Detection

If --workspace is omitted, the script tries:

  1. OPENCLAW_WORKSPACE environment variable
  2. Current directory (if AGENTS.md exists)
  3. ~/.openclaw/workspace (default)

What Gets Monitored

CategoryFilesAlert Level on Change
CriticalSOUL.md, AGENTS.md, IDENTITY.md, USER.md, TOOLS.md, HEARTBEAT.mdWARNING
Memorymemory/*.md, MEMORY.mdINFO (expected to change)
Config*.json in workspace rootWARNING
Skillsskills/*/SKILL.mdWARNING

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 issues
  • 1 — 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.